© 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. 13067
    Prev
    Next
    INDEX
    Explanations

    punctuation and special formatting used in legal or formal documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    withIdentifier
    -0.60
    ftagPool
    -0.60
    kháu
    -0.56
    jgl
    -0.55
     wireType
    -0.54
     كومونز
    -0.52
    
    -0.52
     AssemblyTitle
    -0.51
     sna
    -0.50
    TokenNameCOMMA
    -0.49
    POSITIVE LOGITS
     Ohren
    0.35
     https
    0.32
     odkazy
    0.32
     Hentet
    0.31
     aeroporto
    0.30
    ьаж
    0.30
     hän
    0.29
    eamiento
    0.28
    ยม
    0.28
    เลย
    0.28
    Activations Density 0.413%

    No Known Activations