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. 1339
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    60.75
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    nouns and phrases associated with professional expertise and teamwork

    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
     Audiodateien
    -0.47
    zheimer
    -0.41
     mandatory
    -0.41
     SYLLABLE
    -0.40
    arsk
    -0.40
    Mandatory
    -0.40
     commonest
    -0.40
     schick
    -0.38
    blurRadius
    -0.38
    Captor
    -0.38
    POSITIVE LOGITS
     team
    0.59
     Team
    0.55
     TEAM
    0.54
    Team
    0.54
     équipe
    0.53
    team
    0.52
     للمعارف
    0.50
    TEAM
    0.47
     teams
    0.47
    équipe
    0.47
    Activations Density 0.004%

    No Known Activations