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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-9B-IT
    3. 20-AXBENCH-REFT-R1-RES-16K
    4. 6261
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    50
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    numerical data or statistics related to research studies

    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
     ProtoMessage
    -0.69
    SequentialGroup
    -0.60
    :✨
    -0.59
     EconPapers
    -0.50
     jScrollPane
    -0.50
     Drapeau
    -0.50
    </tfoot>
    -0.50
    RectangleBorder
    -0.50
    DockStyle
    -0.49
    amai
    -0.48
    POSITIVE LOGITS
    而非
    0.41
    EndGlobalSection
    0.34
    itrile
    0.33
    four
    0.31
     للاسماء
    0.31
    five
    0.30
    six
    0.30
    kaç
    0.30
    IRQn
    0.29
     duros
    0.29
    Activations Density 0.006%

    No Known Activations