© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-9B-IT
    5. 20-AXBENCH-REFT-R1-RES-16K
    7. 2780
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    46.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    references to handling or manipulating strings and data structures in programming 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
     ujednoznacz
    -0.67
     ویکی‌پدی
    -0.63
    }{*}{
    -0.61
     незавершена
    -0.61
    contentLoaded
    -0.58
     kaarangay
    -0.58
    ➟
    -0.53
    \}.
    -0.53
    MENAFN
    -0.50
     Italijanski
    -0.50
    POSITIVE LOGITS
     suspendu
    0.41
    cityName
    0.40
     solitario
    0.40
     neceff
    0.39
     propOrder
    0.39
    erende
    0.39
     Teknologi
    0.39
     exécu
    0.38
    either
    0.38
    rophoresis
    0.38
    Activations Density 0.059%

    No Known Activations