Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 9877
    Prev
    Next
    INDEX
    Explanations

    networking-related error messages and protocols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     otomatig
    -0.52
    zule
    -0.50
     lade
    -0.50
    󠁣
    -0.49
     Hum
    -0.48
     Brice
    -0.48
     canoe
    -0.47
     Pran
    -0.47
    erski
    -0.46
     Jans
    -0.45
    POSITIVE LOGITS
     كومونز
    0.70
    Socket
    0.70
     socket
    0.69
    socket
    0.69
     sockets
    0.66
     Socket
    0.66
    ثيق
    0.65
    ReusableCell
    0.63
    AnimationsModule
    0.62
    jooq
    0.61
    Activations Density 0.679%

    No Known Activations