© 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. 38-GEMMASCOPE-RES-16K
    11. 7355
    Prev
    Next
    INDEX
    Explanations

    references to file formats and data exchange

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vode
    -0.43
    Tembelea
    -0.32
     مشين
    -0.28
    はじめに
    -0.26
     season
    -0.26
    Season
    -0.26
     cadeira
    -0.26
     tane
    -0.26
     DbSet
    -0.26
     scene
    -0.26
    POSITIVE LOGITS
     format
    3.58
     Format
    3.11
     formats
    3.09
    format
    3.05
    Format
    2.84
     FORMAT
    2.83
     Formats
    2.73
     formato
    2.70
    格式
    2.59
    FORMAT
    2.53
    Activations Density 0.715%

    No Known Activations