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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 9499
    Prev
    Next
    INDEX
    Explanations

    the start of a document or section

    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
    ViewFeatures
    -0.64
    kháu
    -0.63
    InjectAttribute
    -0.62
    DebuggerNonUser
    -0.61
    WillAppear
    -0.58
     MediatR
    -0.57
     Stande
    -0.56
     Zjednoc
    -0.56
    ElementException
    -0.54
     DBNull
    -0.54
    POSITIVE LOGITS
    filepath
    0.71
     filepath
    0.63
    src
    0.56
    BeginContext
    0.52
     CIP
    0.51
    atigable
    0.51
    architecte
    0.48
    filePath
    0.48
     SRC
    0.48
     الحره
    0.47
    Activations Density 0.018%

    No Known Activations