© 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. 35-GEMMASCOPE-RES-16K
    11. 12660
    Prev
    Next
    INDEX
    Explanations

    technical terms and keywords related to web services and messaging protocols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.50
    原标题
    -0.40
    älde
    -0.37
     Burk
    -0.36
     Dynasty
    -0.35
    plastik
    -0.35
     AssemblyCompany
    -0.34
     пробу
    -0.34
     SAR
    -0.34
     competed
    -0.34
    POSITIVE LOGITS
     socket
    0.98
     Socket
    0.90
     WebSocket
    0.90
     websocket
    0.89
     sockets
    0.89
    socket
    0.88
     chat
    0.86
    WebSocket
    0.79
    Socket
    0.78
     rooms
    0.77
    Activations Density 0.257%

    No Known Activations