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. 1081
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    38
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    instances of numbers and punctuation marks that typically signal data or categorizations

    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
     ***!
    -0.42
     nawr
    -0.39
    tagext
    -0.39
    WireFormat
    -0.36
     kommenden
    -0.33
     eigentlich
    -0.31
    <bos>
    -0.31
     adulte
    -0.31
     Thayer
    -0.30
     translateY
    -0.30
    POSITIVE LOGITS
    setVerticalGroup
    0.71
    rrggbb
    0.70
     purpoſe
    0.56
     betweenstory
    0.56
    ſelves
    0.53
     ſtand
    0.52
    IBOutlet
    0.52
    basicConfig
    0.52
    ftance
    0.51
     تضيفلها
    0.50
    Activations Density 5.013%

    No Known Activations