© 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. 10-GEMMASCOPE-RES-16K
    11. 7739
    Prev
    Next
    INDEX
    Explanations

    structured data elements or syntax in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setVerticalGroup
    -0.82
    Personendaten
    -0.68
    Rüyada
    -0.66
     stället
    -0.61
    parsedMessage
    -0.60
     spreken
    -0.59
    новништво
    -0.59
    Попис
    -0.58
    migrationBuilder
    -0.57
    存于互联网档案馆
    -0.57
    POSITIVE LOGITS
     lev
    0.42
     recep
    0.42
     ro
    0.42
    springframework
    0.38
     rep
    0.37
     ven
    0.37
     ra
    0.36
     ab
    0.36
     pen
    0.36
     vib
    0.36
    Activations Density 0.133%

    No Known Activations