© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-9B-IT
    5. 20-AXBENCH-REFT-R1-RES-16K
    7. 525
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    40.75
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    positive attributes and diverse situations regarding tools, roles, or concepts

    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
    retudo
    -0.33
     condena
    -0.33
     nawr
    -0.32
    ::::::::
    -0.30
     pungkas
    -0.29
     mümkün
    -0.27
     itinéraires
    -0.27
    arriver
    -0.27
     namorado
    -0.27
     Negra
    -0.26
    POSITIVE LOGITS
    rrggbb
    0.77
    setVerticalGroup
    0.74
     propOrder
    0.69
     initComponents
    0.63
    ꎬ
    0.60
     beſti
    0.59
    <2mass>
    0.59
    𞤫
    0.59
     Ror
    0.58
    <unused72>
    0.58
    Activations Density 7.352%

    No Known Activations