© 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. 3235
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    45
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    programming language keywords and syntax structures

    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
    ChildScrollView
    -0.81
     betweenstory
    -0.80
     nonUne
    -0.80
     незавершена
    -0.76
    expandindo
    -0.73
     Autorizaciones
    -0.69
    ंदीखरीदारी
    -0.68
     noDo
    -0.67
     intptr
    -0.66
     дописавши
    -0.65
    POSITIVE LOGITS
    Biografía
    0.35
     suspendu
    0.34
     either
    0.33
    XmlAccessorType
    0.33
    Either
    0.30
     BROTHERS
    0.30
    ;
    0.30
     secundario
    0.29
     provecho
    0.29
    AllowAnonymous
    0.29
    Activations Density 0.073%

    No Known Activations