© 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. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 70121
    Prev
    Next
    INDEX
    Explanations

    elements related to programming structure and syntax in a coding context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Java class and method definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    請繼續往下閱讀
    -0.37
    testify
    -0.35
     Lage
    -0.34
     Sucher
    -0.34
     onPostExecute
    -0.33
    ConstraintMaker
    -0.32
    laga
    -0.32
    iese
    -0.31
    บ้าง
    -0.31
     sacré
    -0.31
    POSITIVE LOGITS
     InputDecoration
    0.62
    routeProvider
    0.60
     initComponents
    0.52
    ItemBackground
    0.51
    @[+][
    0.50
    internalType
    0.48
     StatefulWidget
    0.48
     صوتيه
    0.47
     otomatig
    0.47
     simulate
    0.46
    Activations Density 0.030%

    No Known Activations