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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 3-GEMMASCOPE-RES-16K
    6. 10239
    Prev
    Next
    INDEX
    Explanations

    references to document pagination and page numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HostException
    -0.59
    SPJ
    -0.54
     glyphicon
    -0.53
    orylation
    -0.52
    ği
    -0.49
    UpdateCommand
    -0.49
    ticides
    -0.49
    SHIPS
    -0.49
    Cep
    -0.49
     CURIAM
    -0.48
    POSITIVE LOGITS
    Pages
    2.76
    pages
    2.49
     Pages
    2.37
     pages
    2.31
     PAGES
    1.94
    PAGES
    1.81
     páginas
    1.37
    Páginas
    1.33
     pagine
    1.16
     Seiten
    1.01
    Activations Density 0.122%

    No Known Activations