© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 3803
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to the XML document processing and schema validation

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

    followed by "document" or "Document"

    np_acts-logits-general · gemini-2.0-flash

    document, documents, doc

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebMethod
    -0.59
    ReusableCell
    -0.54
     larvae
    -0.53
     larva
    -0.53
    ThroughAttribute
    -0.52
    喱
    -0.52
    MetaType
    -0.51
     Natale
    -0.50
    centerline
    -0.49
     himo
    -0.48
    POSITIVE LOGITS
     document
    3.60
     Document
    3.29
    document
    3.26
    Document
    3.13
     doc
    2.90
     DOCUMENT
    2.82
     documents
    2.81
     Doc
    2.70
    Doc
    2.67
    doc
    2.63
    Activations Density 0.177%

    No Known Activations