© 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
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 8547
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and structure, particularly in a code context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    OGND
    -0.65
     propOrder
    -0.52
     unknownFields
    -0.50
    addCriterion
    -0.48
    bcryptjs
    -0.48
     curvas
    -0.47
     المعيارى
    -0.46
    ArrowToggle
    -0.45
     regalías
    -0.42
    indépendance
    -0.42
    POSITIVE LOGITS
    ToAction
    0.52
    帖最后由
    0.44
    loginPage
    0.44
     online
    0.44
     IActionResult
    0.43
    IRQn
    0.42
    Parcelize
    0.42
    ViewFeatures
    0.42
     naselje
    0.42
     Ther
    0.41
    Activations Density 0.053%

    No Known Activations