© 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. 20-GEMMASCOPE-RES-16K
    11. 4132
    Prev
    Next
    INDEX
    Explanations

    source code elements and comments in programming languages

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

    source code metadata like creation dates, copyright notices, and import statements from various programming files.

    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
    ########.
    -0.75
     kasarigan
    -0.64
    таратура
    -0.62
    ReusableCell
    -0.62
    StoryboardSegue
    -0.59
    Hentet
    -0.59
     BrowserModule
    -0.59
    RenderAtEndOf
    -0.58
    SharedCtor
    -0.58
    findpost
    -0.58
    POSITIVE LOGITS
     Sorge
    0.34
     počas
    0.33
     PhpStorm
    0.33
     Streifen
    0.33
     scio
    0.31
    {{/
    0.31
     Independencia
    0.30
     Stadtteil
    0.30
     Kreise
    0.30
     unleashed
    0.29
    Activations Density 0.059%

    No Known Activations