Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-9B-IT
    3. 20-AXBENCH-REFT-R1-RES-16K
    4. 5284
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    35.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    patterns and structures in text, particularly focusing on character and formatting conventions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    pyvene/gemma-reft-r1-9b-it-res/l20
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.50
    RTDA
    -0.40
     Audiodateien
    -0.38
     Paglinawan
    -0.38
     sumpay
    -0.37
     Roskov
    -0.37
    Recurring
    -0.36
    resizingMask
    -0.35
     المتحدة
    -0.35
    揄
    -0.35
    POSITIVE LOGITS
    bibfield
    0.56
    phazard
    0.53
     propOrder
    0.46
    DIPSETTING
    0.46
    AutoresizingMask
    0.46
     queſta
    0.46
    ighborhood
    0.44
    InitVars
    0.44
     purpoſe
    0.44
     contextLoads
    0.43
    Activations Density 0.973%

    No Known Activations