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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-9B-IT
    5. 20-AXBENCH-REFT-R1-RES-16K
    7. 3881
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    50.75
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    instances of numerical values or mathematical operations

    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
     يتيمه
    -0.59
    RenderAtEndOf
    -0.58
    Бахар
    -0.57
     ब्रेकडाउन
    -0.56
     ModelExpression
    -0.52
     Wikimedijinoj
    -0.52
     незавершена
    -0.51
     intptr
    -0.51
     мәкал
    -0.50
    tagHelperRunner
    -0.48
    POSITIVE LOGITS
    íté
    0.40
    AntiForgeryToken
    0.38
    InstrumentedTest
    0.38
    utare
    0.35
     DbSet
    0.33
     but
    0.33
     onFailure
    0.32
    而非
    0.32
    imize
    0.32
    ModelSerializer
    0.32
    Activations Density 0.001%

    No Known Activations