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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-9B-IT
    3. 20-AXBENCH-REFT-R1-RES-16K
    4. 66
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    41.75
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    terms related to legal definitions and citations

    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
     nawr
    -0.36
     foot
    -0.35
    ']}
    -0.34
    Salta
    -0.34
     świ
    -0.30
    PyExc
    -0.30
    windowFixed
    -0.30
    latt
    -0.29
    ricians
    -0.29
     miteinander
    -0.29
    POSITIVE LOGITS
    
    0.67
    исленность
    0.59
    TemporalType
    0.56
    bibfield
    0.55
    MigrationBuilder
    0.54
     purpoſe
    0.53
    transQ
    0.51
     ſtand
    0.51
    
    0.51
     EnglishChoose
    0.50
    Activations Density 3.973%

    No Known Activations