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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-9B-IT
    3. 20-AXBENCH-REFT-R1-RES-16K
    4. 34
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    57.75
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    terms related to notation and variable definitions in mathematical 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
     ब्रेकडाउन
    -0.47
    󠁢
    -0.35
    </blockquote>
    -0.34
    󠁣
    -0.34
     immoral
    -0.34
     مغ
    -0.34
    UpInside
    -0.34
    '
    -0.34
    CDs
    -0.33
    unków
    -0.33
    POSITIVE LOGITS
    InstrumentedTest
    0.68
    principalTable
    0.66
    LookAnd
    0.63
    PerformLayout
    0.57
    esModule
    0.57
     '\\;'
    0.55
     kasarigan
    0.52
    تقاوى
    0.50
     Италијани
    0.49
    fromnode
    0.48
    Activations Density 0.004%

    No Known Activations