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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-9B-IT
    3. 20-AXBENCH-REFT-R1-RES-16K
    4. 2736
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    51.25
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    function definitions and method declarations in code

    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
     dapur
    -0.38
     hendes
    -0.38
     retratos
    -0.38
     niebla
    -0.37
     Económica
    -0.35
     olvides
    -0.35
     někdo
    -0.34
     acuarela
    -0.34
     mediodía
    -0.33
     Italij
    -0.33
    POSITIVE LOGITS
    WithIOException
    0.84
    Искәрмәләр
    0.81
     informée
    0.71
    Біографія
    0.68
    XmlAccessorType
    0.67
    исленность
    0.67
    setVerticalGroup
    0.66
    LayoutStyle
    0.66
    DebuggerStep
    0.66
    rrggbb
    0.65
    Activations Density 0.010%

    No Known Activations