© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 13-GEMMASCOPE-RES-16K
    11. 4267
    Prev
    Next
    INDEX
    Explanations

    Structured data and protocols related to networking, particularly focusing on UDP and IP header elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.56
    новниш
    -0.56
    OCCURRED
    -0.55
    StoryboardSegue
    -0.47
    AndEndTag
    -0.47
    pushFollow
    -0.45
    moj
    -0.42
    rifuge
    -0.42
    (;;)
    -0.42
     Refined
    -0.41
    POSITIVE LOGITS
    tinyos
    0.57
     sockaddr
    0.50
     packet
    0.47
     packets
    0.46
    Datagram
    0.44
    packet
    0.44
     Packet
    0.43
     GoogleFonts
    0.41
     Versammlung
    0.41
    packets
    0.40
    Activations Density 0.905%

    No Known Activations