© 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. 3810
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    67.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    important transitional phrases that highlight significant points or emphasize crucial information

    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
    Smarty
    -0.65
    estacks
    -0.63
     AssemblyCulture
    -0.62
    :✨
    -0.62
     ✭✭
    -0.62
    şört
    -0.62
    celled
    -0.61
    ikusbot
    -0.61
    doria
    -0.61
     bluetooth
    -0.60
    POSITIVE LOGITS
     importance
    0.42
     importancia
    0.42
     significance
    0.37
    éndole
    0.37
    importanza
    0.36
     pertinentes
    0.35
     importância
    0.35
     fundamentales
    0.35
     crucial
    0.34
     dôle
    0.32
    Activations Density 0.005%

    No Known Activations