© 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. 3759
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    56.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    specific keywords and phrases that indicate an emphasis on certain terms or punctuation for clarity

    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
     nawr
    -0.34
     Wunsch
    -0.31
     officially
    -0.31
    するための
    -0.31
    ebenarnya
    -0.30
    otoro
    -0.30
    льт
    -0.30
    cookieParser
    -0.30
    ).__
    -0.29
     
    -0.29
    POSITIVE LOGITS
     kasarigan
    0.79
    ########.
    0.68
     '\\;'
    0.65
    +#+#
    0.63
     queſta
    0.63
     feroit
    0.62
    ViewInit
    0.60
     CreateTagHelper
    0.60
     ExecuteAsync
    0.59
    addCriterion
    0.57
    Activations Density 1.793%

    No Known Activations