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. 1115
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    43.75
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    specific punctuation marks and grammatical structures in the 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
     esternos
    -0.59
    GraphicsUnit
    -0.54
    şört
    -0.53
     ModelExpression
    -0.52
    $_['
    -0.45
    :✨
    -0.45
    WriteTagHelper
    -0.45
    ponses
    -0.45
    tagHelperRunner
    -0.44
    Bakgrunnsstoff
    -0.44
    POSITIVE LOGITS
    setVerticalGroup
    0.53
    LookAnd
    0.47
    AutoScaleMode
    0.40
    PerformLayout
    0.39
    basicConfig
    0.39
     betweenstory
    0.38
     ragioni
    0.35
    BoxShadow
    0.35
    NamedQueries
    0.35
    providedIn
    0.34
    Activations Density 0.184%

    No Known Activations