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. 2713
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    53.25
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    specific symbols or structured elements in code or data notation

    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
    :✨
    -0.68
    UnusedPrivate
    -0.68
    Personendaten
    -0.66
     Audiodateien
    -0.63
    المشاركات
    -0.63
    ſcher
    -0.63
    出版年
    -0.63
    gameserver
    -0.59
    mpagne
    -0.59
    tyimages
    -0.58
    POSITIVE LOGITS
     relación
    0.33
     parfois
    0.32
     ámbitos
    0.30
     relacionado
    0.29
     muestra
    0.29
     שי
    0.28
     různ
    0.28
     emplois
    0.28
     variadas
    0.28
     use
    0.28
    Activations Density 0.011%

    No Known Activations