© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1425
    Prev
    Next
    INDEX
    Explanations

    code-related syntax and symbols, particularly those associated with imports and components in programming

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

    Tokens starting with "@" or "/"

    np_acts-logits-general · gemini-2.0-flash

    module imports / paths

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    ChildScrollView
    -0.75
    parsedMessage
    -0.65
     CURIAM
    -0.62
    PointerException
    -0.59
     canst
    -0.58
    CastException
    -0.57
    routeProvider
    -0.57
    usermodel
    -0.57
    balleur
    -0.56
     MainAxisSize
    -0.56
    POSITIVE LOGITS
     '@
    1.09
     "@
    0.92
    ("@
    0.66
    ('@
    0.63
    "@
    0.63
    '@
    0.58
     "@/
    0.46
    ="@
    0.45
    /@
    0.43
    .@
    0.41
    Activations Density 0.013%

    No Known Activations