© 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. 4803
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    77
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    terms related to pharmacological and biochemical concepts in medical contexts

    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
     Paglinawan
    -0.51
    Smarty
    -0.50
     ***!
    -0.50
     electrically
    -0.44
    styleType
    -0.43
     وتسجيلات
    -0.43
     elettrica
    -0.43
    brida
    -0.42
    httphttps
    -0.42
     allAfrica
    -0.41
    POSITIVE LOGITS
     betweenstory
    0.57
    fromnode
    0.54
    NoSuchAlgorithm
    0.44
    DispatchToProps
    0.43
     farmacia
    0.42
    InstrumentedTest
    0.42
    ActionCreators
    0.42
     lucha
    0.41
     laboratory
    0.40
     utilization
    0.40
    Activations Density 0.011%

    No Known Activations