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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 15623
    Prev
    Next
    INDEX
    Explanations

    mentions of academic institutions and their associated departments or research centers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Between institution names and locations

    np_acts-logits-general · gemini-2.0-flash

    institutions and laboratories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adaptiveStyles
    -0.61
     @"/
    -0.61
     समीक्षाओं
    -0.57
     propOrder
    -0.54
    transQ
    -0.53
    QApplication
    -0.52
     Verw
    -0.52
     становника
    -0.52
     SwiftUI
    -0.52
    .*")]
    -0.51
    POSITIVE LOGITS
     Institute
    0.79
     Labor
    0.79
    Labor
    0.77
     laboratoire
    0.77
     Laboratory
    0.75
     laboratory
    0.72
     Centre
    0.71
    labor
    0.70
     University
    0.70
     laboratories
    0.69
    Activations Density 0.537%

    No Known Activations