© 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. 2315
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    63
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    various types of technical and scientific terminology related to processes and measurements

    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
     Audiodateien
    -0.34
     vapour
    -0.32
    AnchorStyles
    -0.31
     hydrostatic
    -0.31
    newArrayList
    -0.31
     famously
    -0.31
     inhale
    -0.31
     risen
    -0.30
    httphttps
    -0.30
    DCHECK
    -0.30
    POSITIVE LOGITS
     betweenstory
    0.77
    fromnode
    0.73
     ſta
    0.70
     purpoſe
    0.69
    transQ
    0.63
    IntoConstraints
    0.60
    ſelf
    0.59
    MigrationBuilder
    0.56
    ſelves
    0.55
     ſol
    0.54
    Activations Density 1.836%

    No Known Activations