© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 84395
    Prev
    Next
    INDEX
    Explanations

    terminology related to network sockets in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    socket, network, programming, code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -0.35
    Parameteri
    -0.33
    ebilir
    -0.32
     Fortun
    -0.32
     clever
    -0.32
     macron
    -0.31
    たり
    -0.30
     Terra
    -0.30
    Amp
    -0.30
    hrung
    -0.29
    POSITIVE LOGITS
    Socket
    2.56
     Socket
    1.85
    Sockets
    1.14
    ServerSocket
    1.09
    SOCKET
    0.89
     Sock
    0.84
     socket
    0.84
    Sock
    0.83
    sockets
    0.79
    SocketChannel
    0.76
    Activations Density 0.001%

    No Known Activations