© 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. 450
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    60
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    qualities and traits related to characters or abilities, often in specific contexts like gaming or professions

    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
     AssemblyCulture
    -0.63
     Audiodateien
    -0.57
     esternos
    -0.56
    LabelTagHelper
    -0.56
    tovers
    -0.56
    $_['
    -0.55
    ⤒
    -0.55
    出版年
    -0.53
    лтемелер
    -0.53
     commonest
    -0.53
    POSITIVE LOGITS
     role
    0.41
     skills
    0.39
     roles
    0.39
     character
    0.36
     characters
    0.33
     skill
    0.33
     arche
    0.32
    戏
    0.31
     team
    0.31
    work
    0.31
    Activations Density 0.001%

    No Known Activations