© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-9B-IT
    5. 20-AXBENCH-REFT-R1-RES-16K
    7. 492
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    52
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    function definitions in 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
    WriteTagHelper
    -0.60
     AssemblyCulture
    -0.49
    -------------</
    -0.47
     Italijanski
    -0.40
    Diweddarwch
    -0.40
    </>
    -0.39
     ویکی‌آمباردا
    -0.39
    MessageOf
    -0.39
    )」
    -0.38
    '/>
    -0.38
    POSITIVE LOGITS
     propOrder
    0.55
    InstrumentedTest
    0.50
    XmlAccessorType
    0.46
    DebuggerStep
    0.43
    tagHelper
    0.43
     Cul
    0.42
     Rob
    0.41
    Cul
    0.41
    Managed
    0.40
    קי
    0.39
    Activations Density 0.055%

    No Known Activations