© 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
    3. Gemma-2-9B-IT
    5. 20-AXBENCH-REFT-R1-RES-16K
    7. 6275
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    15.875
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    numerical values and references to specific people or characters in a narrative context

    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
    ValueStyle
    -0.67
     مشين
    -0.56
    OGND
    -0.49
    haikusbot
    -0.47
    HasAnnotation
    -0.45
     anſ
    -0.45
     SqlParameter
    -0.44
     ſhe
    -0.43
    ImageContext
    -0.43
    WebServlet
    -0.42
    POSITIVE LOGITS
    bria
    0.43
    glow
    0.42
     Rame
    0.42
    throw
    0.40
    blo
    0.40
    cora
    0.40
    +#+#
    0.40
    msgSender
    0.40
    Hyundai
    0.40
     Rogan
    0.40
    Activations Density 0.306%

    No Known Activations