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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 14703
    Prev
    Next
    INDEX
    Explanations

    references to installation, configuration, or setup of software components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tembelea
    -0.48
    endphp
    -0.47
     kaarangay
    -0.47
     <>",
    -0.46
    ScopeManager
    -0.45
     panoramique
    -0.44
    InjectAttribute
    -0.43
     bénévoles
    -0.43
    BeginContext
    -0.43
    InvalidProtocol
    -0.42
    POSITIVE LOGITS
     separate
    3.56
    separate
    3.25
     Separate
    3.17
    Separate
    3.14
     separately
    2.95
     SEPAR
    2.94
     seperate
    2.94
     separat
    2.61
     Separ
    2.59
     separado
    2.59
    Activations Density 1.546%

    No Known Activations