© 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. 6291
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    5.844
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    programming code structure and definitions

    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
    EndContext
    -0.40
    DoubleQuotes
    -0.39
    AddTagHelper
    -0.38
     Suomessa
    -0.36
    OGND
    -0.35
     gouvernements
    -0.34
     ettiği
    -0.34
     Schicks
    -0.33
    awaiter
    -0.33
     nying
    -0.32
    POSITIVE LOGITS
    webElementXpaths
    0.77
    تقاوى
    0.63
     հղումներ
    0.58
     Administrativna
    0.57
    BufferException
    0.54
     فريبيس
    0.54
    HandlerContext
    0.53
    Население
    0.52
     Pear
    0.52
     TR
    0.51
    Activations Density 0.131%

    No Known Activations