© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 4645
    Prev
    Next
    INDEX
    Explanations

    code-related functions and components within a program

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

    JavaScript code structure and syntax elements like function definitions, closing braces, and whitespace/indentation patterns.

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

    JavaScript code, particularly function definitions and variable declarations.

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

    JavaScript/Node-style source code snippets, including module definitions, function blocks, and browser script sections.

    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
     EconPapers
    -0.56
     للمعارف
    -0.56
    RenderAtEndOf
    -0.54
    tagHelperRunner
    -0.48
     [...
    -0.48
     Promise
    -0.43
    IsContent
    -0.43
     const
    -0.43
    MessageTagHelper
    -0.43
     promise
    -0.42
    POSITIVE LOGITS
    var
    1.11
     var
    0.90
     Var
    0.55
    VAR
    0.51
    Var
    0.50
    varu
    0.49
     VAR
    0.48
    вар
    0.46
     varieties
    0.43
     ISNI
    0.42
    Activations Density 0.222%

    No Known Activations