© 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. 24-GEMMASCOPE-RES-16K
    11. 12275
    Prev
    Next
    INDEX
    Explanations

    structural elements and attributes commonly found in XML or HTML documents

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

    "/TR/" within URLs

    np_acts-logits-general · gemini-2.0-flash

    W3C technical reports and XML namespaces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wikimedijinoj
    -0.77
     समीक्षाओं
    -0.66
    SourceChecksum
    -0.66
    :✨
    -0.63
     مرئيه
    -0.62
    FunctionFlags
    -0.59
    Amicalement
    -0.59
     iconLine
    -0.58
     تكبرها
    -0.56
     decry
    -0.56
    POSITIVE LOGITS
    XMLSchema
    0.54
    FXML
    0.52
     Brandt
    0.46
    pulo
    0.46
    araan
    0.46
    Padding
    0.44
    eced
    0.44
    其次
    0.43
    &&\
    0.42
    vnd
    0.41
    Activations Density 0.286%

    No Known Activations