© 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. 504
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    36.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    references to legal terms and court cases

    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
    /
    -0.31
     
    -0.31
    (
    -0.31
     peringatan
    -0.31
     expectativa
    -0.30
     sür
    -0.30
    -
    -0.30
    )
    -0.29
     başar
    -0.29
     wirklich
    -0.28
    POSITIVE LOGITS
    rrggbb
    0.79
     насељу
    0.77
    
    0.75
     autorytatywna
    0.73
     يتيمه
    0.72
    RTCF
    0.70
     للاسماء
    0.70
     betweenstory
    0.69
    setVerticalGroup
    0.69
     Normdatei
    0.67
    Activations Density 3.957%

    No Known Activations