Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-9B-IT
    3. 20-AXBENCH-REFT-R1-RES-16K
    4. 831
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    40.25
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    elements related to legal analysis and courtroom context

    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
    tagext
    -0.41
     ***!
    -0.39
     nawr
    -0.34
     eğ
    -0.33
     foot
    -0.32
     
    -0.32
    MessageOf
    -0.31
    veröffentlichung
    -0.30
     legais
    -0.29
     cref
    -0.29
    POSITIVE LOGITS
    setVerticalGroup
    0.64
     betweenstory
    0.63
    ſelves
    0.61
    rrggbb
    0.60
    ſelf
    0.57
     purpoſe
    0.57
    ftance
    0.57
     itſelf
    0.57
     erſten
    0.56
    <unused14>
    0.55
    Activations Density 4.310%

    No Known Activations