© 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. 9245
    Prev
    Next
    INDEX
    Explanations

    references to notifications and alert mechanisms

    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
    Personendaten
    -0.83
     Италијани
    -0.68
    fromnode
    -0.62
     tartalomajánló
    -0.57
     nahilalakip
    -0.57
     Italijanski
    -0.57
    TagMode
    -0.57
     parceria
    -0.56
     gdyby
    -0.56
     '\\;'
    -0.56
    POSITIVE LOGITS
     notification
    0.86
    notification
    0.78
     numerical
    0.68
     notifications
    0.66
     Notification
    0.55
     Numerical
    0.53
     statistics
    0.52
    notific
    0.52
     notific
    0.52
     protest
    0.51
    Activations Density 0.215%

    No Known Activations