© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 5920
    Prev
    Next
    INDEX
    Explanations

    LaTeX document structure and formatting commands, particularly those related to document classes, packages, and section headings.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    elements of document structure and metadata in scientific or technical writing.

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

    LaTeX code related to document formatting, includes commands, figure placement, and document structure.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    before labels or captions

    np_acts-logits-general · gemini-2.0-flash

    document metadata and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    GenerationType
    -0.55
    Hochspringen
    -0.51
    HandlerContext
    -0.51
    Kanpo
    -0.49
     Berto
    -0.49
    ScopeManager
    -0.48
    HomeAsUpEnabled
    -0.46
     nasled
    -0.44
     seura
    -0.43
    kswagen
    -0.43
    POSITIVE LOGITS
    Datuak
    0.68
     referenties
    0.68
    AccessorTable
    0.65
    featureID
    0.60
    SharedCtor
    0.60
    SourceChecksum
    0.58
     writeTo
    0.58
    Obrázky
    0.55
    InvalidProtocol
    0.55
    зулта
    0.55
    Activations Density 0.061%

    No Known Activations