Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-9B-IT
    3. 20-AXBENCH-REFT-R1-RES-16K
    4. 1231
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    48.75
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    passages that include punctuation or formatting elements often found in written text

    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
    醐
    -0.46
     Schild
    -0.44
    éez
    -0.41
    şört
    -0.38
     switch
    -0.36
     aras
    -0.36
     nere
    -0.36
     reproduce
    -0.35
    isième
    -0.35
    ėte
    -0.34
    POSITIVE LOGITS
    LookAnd
    0.68
    PerformLayout
    0.57
    ValueStyle
    0.54
    InstrumentedTest
    0.51
     contextLoads
    0.51
     purpoſe
    0.50
    ſelf
    0.49
    帖最后由
    0.48
    BoxShadow
    0.48
    setVerticalGroup
    0.47
    Activations Density 2.686%

    No Known Activations