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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-9B-IT
    3. 20-AXBENCH-REFT-R1-RES-16K
    4. 715
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    73.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    words and phrases related to applause or expressions of approval

    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
     diagnose
    -0.43
     telo
    -0.40
     Diagnose
    -0.39
     Samaria
    -0.38
     superintend
    -0.38
    tovers
    -0.37
    openqa
    -0.37
    лтемелер
    -0.37
     Gennaio
    -0.36
     AssemblyCulture
    -0.36
    POSITIVE LOGITS
     applause
    0.73
     appla
    0.63
     applauded
    0.59
     applaud
    0.58
    ValueStyle
    0.58
     praise
    0.58
     appreciation
    0.56
     applau
    0.56
    praise
    0.56
     admiration
    0.54
    Activations Density 0.000%

    No Known Activations