© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 13669
    Prev
    Next
    INDEX
    Explanations

    variations and details about products or features that allow for customization and different options

    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
     genoux
    -0.44
     épaules
    -0.41
     journées
    -0.32
    sag
    -0.31
     برانيه
    -0.31
    쿵
    -0.31
    戬
    -0.31
    isse
    -0.31
    нент
    -0.31
    charCode
    -0.30
    POSITIVE LOGITS
     types
    1.71
     styles
    1.63
     formats
    1.52
     varieties
    1.45
     configurations
    1.30
     TYPES
    1.30
     kinds
    1.29
     tipos
    1.28
    types
    1.27
     flavors
    1.27
    Activations Density 1.256%

    No Known Activations