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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-9B-IT
    5. 20-AXBENCH-REFT-R1-RES-16K
    7. 1538
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    49.25
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    instances of explicit numerical values or amounts

    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
    -0.54
    Eksteraj
    -0.51
     ModelExpression
    -0.50
    WEET
    -0.49
    grandfather
    -0.49
     sweetest
    -0.48
    〗
    -0.47
    SequentialGroup
    -0.47
    RectangleBorder
    -0.46
     jScrollPane
    -0.46
    POSITIVE LOGITS
    EndGlobalSection
    0.42
    而非
    0.41
     للاسماء
    0.40
    GenerationType
    0.39
     instead
    0.37
    DotNetBar
    0.36
    AntiForgeryToken
    0.36
     rather
    0.35
     contextLoads
    0.35
    
    0.35
    Activations Density 0.000%

    No Known Activations