Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 15136
    Prev
    Next
    INDEX
    Explanations

    functions and method calls related to synchronization and resource management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DispatchToProps
    -0.81
    เอง
    -0.60
     JAXBElement
    -0.57
    nsis
    -0.53
     Référence
    -0.52
     configureStore
    -0.50
    ThroughAttribute
    -0.50
    =?,
    -0.49
     deleteUser
    -0.49
    #![
    -0.49
    POSITIVE LOGITS
    Personensuche
    0.66
    osoba
    0.62
     StatefulWidget
    0.48
     énergé
    0.47
     noastre
    0.47
    ngrx
    0.47
     asupra
    0.46
     gjelder
    0.46
     cansado
    0.45
     gäller
    0.44
    Activations Density 0.099%

    No Known Activations