Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-9B-IT
    3. 20-AXBENCH-REFT-R1-RES-16K
    4. 696
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    70
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    terminology related to crystalline structures and phase transitions in materials

    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
    raulic
    -0.58
    bootstrapcdn
    -0.57
     lizenzfreies
    -0.56
    atico
    -0.54
    Hochspringen
    -0.52
    izontal
    -0.51
     Paglinawan
    -0.51
     resultCode
    -0.51
    ribut
    -0.49
     sulphuric
    -0.49
    POSITIVE LOGITS
    fromnode
    0.45
     Prozesse
    0.38
    TEntity
    0.35
     PROCESSES
    0.33
    TypedDataSet
    0.33
     processes
    0.32
    PhysRev
    0.32
     muestras
    0.32
    quele
    0.32
    HandlerContext
    0.32
    Activations Density 0.004%

    No Known Activations