© 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. 12450
    Prev
    Next
    INDEX
    Explanations

    references to figures and results in a scientific context

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

    references to figures, tables, or visual elements in academic or scientific papers.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered 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
     ब्रेकडाउन
    -1.09
    parsedMessage
    -1.00
     autorytatywna
    -0.98
    UserScript
    -0.95
     мәкал
    -0.90
    Ӕ
    -0.86
     resourceCulture
    -0.86
     незавершена
    -0.84
     Photocase
    -0.84
    +#+
    -0.83
    POSITIVE LOGITS
     results
    0.52
     showing
    0.41
     Ergebnisse
    0.38
     comparison
    0.38
     result
    0.36
     comparisons
    0.35
     Sieger
    0.35
     hasil
    0.35
     resultados
    0.35
     striking
    0.34
    Activations Density 0.866%

    No Known Activations