© 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. 8552
    Prev
    Next
    INDEX
    Explanations

    Java programming language keywords and structure

    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
    featureID
    -0.66
     cherchés
    -0.64
     AssemblyCompany
    -0.64
    +#+
    -0.63
     AssemblyTitle
    -0.61
    الدراسه
    -0.61
    hoeddwyd
    -0.59
    addCriterion
    -0.57
     SqlDbType
    -0.56
     الرياضيه
    -0.56
    POSITIVE LOGITS
    setVerticalGroup
    0.35
    SuspendLayout
    0.31
     floor
    0.31
     cáo
    0.30
     Driscoll
    0.30
     assurent
    0.30
    Observable
    0.29
    ->
    0.28
    subsubsection
    0.28
     geni
    0.28
    Activations Density 0.032%

    No Known Activations