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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 1248
    Prev
    Next
    INDEX
    Explanations

    terms related to socket and network programming

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

    Code related to sockets

    np_acts-logits-general · gemini-2.0-flash

    socket programming

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     StatelessWidget
    -0.44
     templado
    -0.34
    amentul
    -0.34
     Picchu
    -0.34
    casian
    -0.34
     poesía
    -0.33
     asesinado
    -0.33
    interopRequire
    -0.32
     mármol
    -0.32
     Kegiatan
    -0.32
    POSITIVE LOGITS
    netinet
    0.82
     sockaddr
    0.76
    rinfo
    0.70
    sockets
    0.64
    Sockets
    0.61
    ServerSocket
    0.60
    SocketAddress
    0.60
    sockfd
    0.59
    PMailer
    0.59
     Socket
    0.58
    Activations Density 0.410%

    No Known Activations