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. 954
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    6.031
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    prominent film titles and notable figures in narrative contexts

    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
     type
    -0.36
    IBAction
    -0.34
     ianuarie
    -0.32
     jsonify
    -0.31
     Cataloging
    -0.30
     naman
    -0.30
    mbggenerated
    -0.29
    hObject
    -0.29
     types
    -0.29
     recursive
    -0.29
    POSITIVE LOGITS
    CppCodeGen
    0.73
     мәкал
    0.63
    ThroughAttribute
    0.60
    RenderAtEndOf
    0.60
    UrlResolution
    0.60
    ViewFeatures
    0.59
     HttpNotFound
    0.59
    Хьажоргаш
    0.58
    StoryboardSegue
    0.57
     surla
    0.57
    Activations Density 0.052%

    No Known Activations