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. 1190
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    48.25
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    declarations and initializations of variables in programming code

    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
    Aholisi
    -0.52
     pungkas
    -0.45
    tagHelperRunner
    -0.44
     }}-
    -0.39
    StructEnd
    -0.38
    WireFormat
    -0.37
    assertRaises
    -0.36
     "").
    -0.36
    nextInt
    -0.35
    Népesség
    -0.35
    POSITIVE LOGITS
    
    0.57
    separate
    0.47
     propOrder
    0.47
    Separate
    0.45
    spl
    0.44
     Variable
    0.43
     Normdatei
    0.43
    InstrumentedTest
    0.43
    IntoConstraints
    0.43
    SuppressLint
    0.42
    Activations Density 2.893%

    No Known Activations