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. 2760
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    63.75
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    references to molecular interactions and structures in biomedical contexts

    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
    -0.54
    TokenNameDOT
    -0.53
     hydrostatic
    -0.50
    Smarty
    -0.49
     FetchType
    -0.49
     surla
    -0.48
     Walkover
    -0.48
    YourGuide
    -0.48
     lizenzfreies
    -0.48
     ModelExpression
    -0.48
    POSITIVE LOGITS
     relationships
    0.36
     muestra
    0.34
    
    0.34
     relación
    0.33
    TypedDataSet
    0.32
     termé
    0.32
    ########.
    0.31
    xtures
    0.30
     forbin
    0.30
     relationship
    0.30
    Activations Density 0.017%

    No Known Activations