© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-9B-IT
    5. 20-AXBENCH-REFT-R1-RES-16K
    7. 5869
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    52.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    numbers, specifically those relating to counts or measurements

    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
    Бахар
    -0.70
     незавершена
    -0.64
    المناصب
    -0.56
     ProtoMessage
    -0.54
    RectangleBorder
    -0.53
     FetchType
    -0.52
    </caption>
    -0.52
     ivelany
    -0.51
     EconPapers
    -0.50
    WEET
    -0.50
    POSITIVE LOGITS
    íté
    0.40
     dispuestos
    0.35
    itrile
    0.34
     للاسماء
    0.34
     instead
    0.34
    
    0.34
     forfait
    0.33
    IBOutlet
    0.32
    而非
    0.32
    AntiForgeryToken
    0.31
    Activations Density 0.000%

    No Known Activations