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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7023
    Prev
    Next
    INDEX
    Explanations

    structural elements and headers within a document

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

    code-related tokens and syntax like includes, preprocessor directives, and programming language constructs.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    structural markers in technical text, such as diff/patch additions, quoted reply lines, and file or document starts.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    newlines or line breaks in source code or structured text documents.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    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
    twimg
    -0.64
    adpleegd
    -0.54
     tartalomajánló
    -0.47
     Accesorios
    -0.43
     Zweig
    -0.43
     pamięci
    -0.42
     Democrá
    -0.42
     destek
    -0.42
     comunión
    -0.41
     Castell
    -0.41
    POSITIVE LOGITS
    fromnode
    0.56
     متحده
    0.50
    CIUDAD
    0.49
    ViewImports
    0.47
     Flix
    0.46
    xam
    0.45
    scriptcase
    0.45
     Nationwide
    0.44
    ]")]
    0.44
     Itself
    0.44
    Activations Density 0.123%

    No Known Activations