© 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. 4848
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    62.25
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    legal terms and concepts associated with court proceedings and litigation

    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
    styleType
    -0.60
    Personendaten
    -0.57
     ویکی‌پدیای
    -0.56
     Audiodateien
    -0.53
    SequentialGroup
    -0.52
    arangay
    -0.52
    bootstrapcdn
    -0.51
     ویکی
    -0.50
    NOUNC
    -0.50
     esternos
    -0.50
    POSITIVE LOGITS
    fromnode
    0.41
    FormState
    0.41
    LookAnd
    0.40
    ValueStyle
    0.37
     evidence
    0.37
     cases
    0.36
     decisions
    0.35
     proceeding
    0.35
     judge
    0.34
     judicia
    0.34
    Activations Density 0.003%

    No Known Activations