© 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. 5694
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    42.75
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    punctuation and formatting elements to identify sentence boundaries and structure

    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
    windowFixed
    -0.36
     Initialized
    -0.35
     uParam
    -0.33
     assumed
    -0.33
     gynhyrchwyd
    -0.31
     foot
    -0.31
     yapan
    -0.31
    Estou
    -0.30
     cref
    -0.29
    tagext
    -0.29
    POSITIVE LOGITS
     виправивши
    0.62
    bibfield
    0.61
     Administrativna
    0.57
    InjectAttribute
    0.56
    发表于
    0.56
    setVerticalGroup
    0.55
    RegressionTest
    0.55
     Meksiku
    0.53
    ToProps
    0.53
    AccessLevel
    0.52
    Activations Density 1.311%

    No Known Activations