© 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. 0-GEMMASCOPE-RES-16K
    11. 3180
    Prev
    Next
    INDEX
    Explanations

    mentions of events or event-related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Britannique
    -0.34
    )}_
    -0.32
    )}_{
    -0.31
     norske
    -0.30
     dokun
    -0.29
     uitges
    -0.29
    kracht
    -0.28
     приста
    -0.28
    колеп
    -0.28
     cirrhosis
    -0.28
    POSITIVE LOGITS
     event
    3.63
     Event
    3.33
     events
    3.31
     EVENT
    3.20
     evento
    3.17
     Events
    3.16
    event
    3.00
    Event
    2.98
     eventos
    2.94
    EVENT
    2.88
    Activations Density 0.290%

    No Known Activations