Close Menu
techwavedispatch.com

    Subscribe to Updates

    Get the latest creative news from FooBar about art, design and business.

    What's Hot

    Explainability of genotype embedding models through observed cohort paths

    November 21, 2026

    [2602.12107] On the Complexity of Offline Reinforcement Learning with Q*-Approximation and Partial Coverage

    November 21, 2026

    Extending Rademacher Complexity-Based Generalization Theory to Domain Generalization

    November 21, 2026
    Facebook X (Twitter) Instagram
    Trending
    • Explainability of genotype embedding models through observed cohort paths
    • [2602.12107] On the Complexity of Offline Reinforcement Learning with Q*-Approximation and Partial Coverage
    • Extending Rademacher Complexity-Based Generalization Theory to Domain Generalization
    • Hostinger Promo Code: 85% Off for November 2026
    • [2511.22031] Predicting Public Health Impacts of Electricity Usage
    • Mint Mobile Discounts for November 2026
    • A Structure-Agnostic, Chemically Informed Slot-Attention Framework for Demixing 1D $^1$H-NMR Mixture Spectra
    • HostGator Coupon Codes: 76% Off Hosting in November 2026
    Facebook X (Twitter) Instagram
    techwavedispatch.com
    Subscribe
    Saturday, November 21
    • Home
    • AI Tools & Software
    • Machine Learning
    • Generative AI
    • Robotics & Automation
    • Future Tech & Hardware
    • AI in Business
    • Ethics & Regulations
    • More
      • Gadgets & Smart Devices
      • Cybersecurity & AI
      • Tech Breakthroughs
    techwavedispatch.com
    Home»Machine Learning»Refusal Register is Causally Steerable: Decomposing the Refusal Direction into Category-Aligned Components in Gemma-2-9B-IT
    Machine Learning

    Refusal Register is Causally Steerable: Decomposing the Refusal Direction into Category-Aligned Components in Gemma-2-9B-IT

    adminBy adminNovember 17, 2026No Comments2 Mins Read
    Facebook Twitter Pinterest LinkedIn Tumblr Email
    Refusal Register is Causally Steerable: Decomposing the Refusal Direction into Category-Aligned Components in Gemma-2-9B-IT
    Share
    Facebook Twitter LinkedIn Pinterest Email

    arXiv:2611.20405v1 Announce Type: cross
    Abstract: Prior work shows that refusal in instruction-tuned language models can be ablated by intervening on a single residual-stream direction (Arditi et al., 2024), and more recent work finds multiple refusal-mediating directions and concept cones (Wollschl\”ager et al., 2025). We ask a different question: do refusal-related directions carry information about the register of refusal language – how the model refuses – and not only whether it refuses? In Gemma-2-9B-IT we identify two SVM-derived linear directions (B1 for harmful-content vs. neutral, B2 for self-reference vs. neutral) at layer 20 with cos(B1, B2) = 0.252 (about 75 degrees, substantially non-parallel). Adding the harmful-vs-neutral difference-of-means direction (cosine 0.68 with B1) to the residual stream of self-reference prompts at alpha = 2.0 shifts content-safety vocabulary from 2.55 to 10.37 hits per 100 tokens, while a magnitude-matched random direction produces 1.13-2.16; the model continues to refuse but switches register from meta-style (“as a language model…”) to content-style (“this would be harmful”). The same register-injection effect reproduces qualitatively in Gemma-2-2B-IT at layer 12 (content vocabulary 1.72 -> 6.37 at alpha = 1.0, vs. random control 1.35), with a narrower coherent-injection window than in 9B. The two directions are not symmetric: the B2 -> harmful intervention produces a much smaller register effect, and across ablation, sufficiency, and injection B1’s causal effects are consistently larger than B2’s. We frame this asymmetry as part of the finding: B1 appears to encode both category detection and refusal-vocabulary information, while B2 encodes primarily category detection. We frame the contribution as identifying category-aligned components related to the Arditi-style difference-of-means direction that play distinct functional roles in refusal register.

    CategoryAligned Causally Components Decomposing direction Gemma29BIT Refusal Register Steerable
    Share. Facebook Twitter Pinterest LinkedIn Tumblr Email
    admin
    • Website

    Related Posts

    Explainability of genotype embedding models through observed cohort paths

    November 21, 2026

    [2602.12107] On the Complexity of Offline Reinforcement Learning with Q*-Approximation and Partial Coverage

    November 21, 2026

    Extending Rademacher Complexity-Based Generalization Theory to Domain Generalization

    November 21, 2026
    Leave A Reply Cancel Reply

    Top Posts

    NVIDIA Is Investigating Reports That CEO Jensen Huang Was The Target Of Chinese Spy Efforts

    November 8, 202619 Views

    ADIndex: Layer-Adaptive Sparse Attention Indexing via Group-Level Distillation

    November 11, 20265 Views

    Anthropic releases new Mythos and Fable models amid RSI concerns

    November 9, 20265 Views

    If AGI is so close, why is everyone leaving? The neolabs and their bets

    November 6, 20265 Views
    Don't Miss
    Machine Learning

    Explainability of genotype embedding models through observed cohort paths

    By adminNovember 21, 20260

    arXiv:2611.25681v1 Announce Type: new Abstract: Deep learning models that combine genotypes with neuroimaging predict neurological…

    [2602.12107] On the Complexity of Offline Reinforcement Learning with Q*-Approximation and Partial Coverage

    November 21, 2026

    Extending Rademacher Complexity-Based Generalization Theory to Domain Generalization

    November 21, 2026

    Hostinger Promo Code: 85% Off for November 2026

    November 21, 2026
    About Us

    Welcome to TechWave Dispatch

    At TechWave Dispatch, we bring you the latest news, insights, and developments from the ever-evolving world of technology. Our mission is to keep readers informed about the innovations shaping our digital future.

    From artificial intelligence and machine learning to cybersecurity, robotics, smart devices, and groundbreaking technologies, we cover the topics that matter in today's fast-moving tech landscape.

    Our Picks

    Explainability of genotype embedding models through observed cohort paths

    November 21, 2026

    [2602.12107] On the Complexity of Offline Reinforcement Learning with Q*-Approximation and Partial Coverage

    November 21, 2026

    Extending Rademacher Complexity-Based Generalization Theory to Domain Generalization

    November 21, 2026
    Most Popular

    After blocking Muse, Amazon now lets users text Alexa to help them shop

    November 6, 20260 Views

    A controlled world for robot learning and evaluation

    November 6, 20260 Views

    Egyptian and Nigerian English join the Open ASR Leaderboard

    November 6, 20260 Views
    Facebook X (Twitter) Instagram Pinterest
    • Terms and Conditions
    • Privacy Policy
    • Contact Us
    • About Us
    © 2026 TechWave Dispatch. All Rights Reserved.

    Type above and press Enter to search. Press Esc to cancel.