© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4431
    Prev
    Next
    INDEX
    Explanations

    references to summaries or summary elements in the text

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

    technical documentation keywords and XML/HTML metadata tags.

    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
     enää
    -0.51
     käytt
    -0.45
     mijne
    -0.43
    voerd
    -0.43
     prochaines
    -0.40
     habet
    -0.39
     næste
    -0.39
     próximas
    -0.39
     maș
    -0.38
     virksom
    -0.37
    POSITIVE LOGITS
    summary
    1.59
     summary
    1.28
    Summary
    1.19
     Summary
    1.17
    SUMMARY
    1.07
     SUMMARY
    1.06
     summaries
    0.97
     summarise
    0.90
     summarize
    0.90
     Summaries
    0.88
    Activations Density 0.020%

    No Known Activations