© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-9B-IT
    5. 20-AXBENCH-REFT-R1-RES-16K
    7. 568
    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

    highly frequent or recurring punctuation marks and formatting elements in the text

    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
    tagext
    -0.54
     utafitiHapana
    -0.49
     AssemblyVersion
    -0.49
     ✭✭
    -0.48
     referenties
    -0.47
    ToAction
    -0.47
    Hochspringen
    -0.47
    󠁣
    -0.46
    isième
    -0.46
    localctx
    -0.45
    POSITIVE LOGITS
    PointerException
    0.41
    fromnode
    0.40
    MathML
    0.38
    árbol
    0.35
     puentes
    0.34
     целях
    0.34
     könnten
    0.33
     StatefulWidget
    0.33
     transfieras
    0.33
     könnte
    0.32
    Activations Density 0.888%

    No Known Activations