© 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. 31-GEMMASCOPE-RES-16K
    6. 15444
    Prev
    Next
    INDEX
    Explanations

    elements and attributes related to scripting and dynamic content in web development

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

    code syntax and programming constructs.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou

    code and technical documentation, particularly HTML attributes, JavaScript variables, and configuration parameters.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    HTML/JavaScript snippets configuring embedded media or script loading, especially involving security and cross-origin settings.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wicidata
    -0.56
     Photocase
    -0.56
    ANTLR
    -0.50
     ब्रेकडाउन
    -0.48
    脚注の使い方
    -0.47
    tonode
    -0.46
    fortawesome
    -0.45
     protoimpl
    -0.45
    EFIAPI
    -0.44
     humain
    -0.44
    POSITIVE LOGITS
     cross
    0.78
     Origin
    0.74
     origin
    0.73
    Origin
    0.72
    跨
    0.72
    origin
    0.71
    cross
    0.69
    CrossOrigin
    0.67
     origins
    0.67
    Origins
    0.66
    Activations Density 0.223%

    No Known Activations