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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 4-GEMMASCOPE-RES-16K
    6. 11030
    Prev
    Next
    INDEX
    Explanations

    programming functions and operations related to defining, applying, and managing templates or data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     StatefulWidget
    -0.77
    WithIOException
    -0.72
     unknownFields
    -0.71
     Audiodateien
    -0.71
    parsedMessage
    -0.70
    OrNil
    -0.70
    localctx
    -0.69
     चीज़ों
    -0.69
     EdgeInsets
    -0.67
    новништво
    -0.67
    POSITIVE LOGITS
     Solve
    0.64
    Prepare
    0.60
     Prepare
    0.59
    ceed
    0.56
    Solve
    0.56
     Preserve
    0.54
    Bind
    0.53
     Promote
    0.53
    tify
    0.53
     Procure
    0.51
    Activations Density 1.197%

    No Known Activations