© 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. 4717
    Prev
    Next
    INDEX
    Explanations

    programming constructs and syntax specific to coding and data structures

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

    assignment statements in code where a variable is assigned a value using the dot notation (e.g., `this.currentCategory = currentCategory`).

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

    variable names and parameters in code, especially in function/method signatures and assignments.

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

    references to object or enum members using dot notation, especially in constructor/getter code and field assignments.

    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
     like
    -0.58
    host
    -0.51
    исленность
    -0.49
     Rap
    -0.48
     Boo
    -0.48
     boo
    -0.47
     Prom
    -0.47
     OST
    -0.46
    '.
    -0.46
    io
    -0.46
    POSITIVE LOGITS
     AssemblyCompany
    0.65
     desmotivaciones
    0.56
     AssemblyTitle
    0.56
     miniaturka
    0.55
    posedge
    0.52
     estadounid
    0.51
    antaranya
    0.51
    apimachinery
    0.49
     damska
    0.48
     Audiodateien
    0.47
    Activations Density 0.384%

    No Known Activations