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. 828
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    54.25
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    mentions of specific roles, significant contributions, and their impact on various subjects

    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
    :✨
    -0.75
    $_['
    -0.67
    httphttps
    -0.66
    AsNil
    -0.63
    andExpect
    -0.63
    WriteTagHelper
    -0.60
     ModelExpression
    -0.60
    tershire
    -0.57
    tovers
    -0.57
     referenties
    -0.54
    POSITIVE LOGITS
    
    0.39
     eksemp
    0.35
    ("'"
    0.30
    known
    0.29
    rawDesc
    0.28
     vicenda
    0.28
    ci
    0.28
     kalangan
    0.28
    avond
    0.28
     вдох
    0.27
    Activations Density 0.000%

    No Known Activations