© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 2114
    Prev
    Next
    INDEX
    Explanations

    references to health-related warnings or precautions

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

    being average or typical

    np_acts-logits-general · gemini-2.0-flash

    average quantities or durations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GenerationType
    -0.49
    liesslich
    -0.48
    nestjs
    -0.48
    achuca
    -0.47
     Obrador
    -0.46
    abank
    -0.45
    ließlich
    -0.45
     dispon
    -0.44
     Whenever
    -0.43
    indelijk
    -0.42
    POSITIVE LOGITS
     typical
    0.85
    中等
    0.81
     average
    0.78
    Typical
    0.76
     durchschnitt
    0.76
     fully
    0.75
     averages
    0.73
     normalt
    0.73
     Typical
    0.70
     medium
    0.68
    Activations Density 0.327%

    No Known Activations