© 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. 5854
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    50.25
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    terms related to definitions, denotations, and descriptions in a mathematical or formal 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
     ब्रेकडाउन
    -0.45
    󠁢
    -0.42
     immoral
    -0.38
    󠁣
    -0.35
    unj
    -0.34
    ˋ
    -0.34
    unków
    -0.34
     oppress
    -0.33
     cheaper
    -0.33
     nerfed
    -0.33
    POSITIVE LOGITS
    LookAnd
    0.73
     '\\;'
    0.73
    InstrumentedTest
    0.63
    setVerticalGroup
    0.60
    AutoScaleMode
    0.59
    esModule
    0.57
     Италијани
    0.57
     Scalars
    0.53
    PreExecute
    0.53
     kasarigan
    0.53
    Activations Density 0.003%

    No Known Activations