© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1050
    Prev
    Next
    INDEX
    Explanations

    file formats and file-related keywords

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

    technical file and data-related terms, especially file extensions and technical acronyms.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    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
    verifyException
    -0.68
    matchCondition
    -0.56
    webElementXpaths
    -0.55
    ResponseWriter
    -0.55
    getColumnIndex
    -0.52
     newOwner
    -0.52
    enterOuterAlt
    -0.51
    География
    -0.50
    +#+#
    -0.50
    ValueStyle
    -0.49
    POSITIVE LOGITS
     XML
    0.60
     xml
    0.58
    xml
    0.58
    XML
    0.57
    Xml
    0.52
     Xml
    0.51
    fxml
    0.48
    yaml
    0.45
     yaml
    0.44
     csv
    0.42
    Activations Density 0.294%

    No Known Activations