© 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. 22-GEMMASCOPE-RES-16K
    11. 6734
    Prev
    Next
    INDEX
    Explanations

    events or actions related to legal or political developments

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

    Sentences ending in a period

    np_acts-logits-general · gemini-2.0-flash

    number of articles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     infine
    -0.73
     another
    -0.72
     then
    -0.68
     lastly
    -0.66
    Referanser
    -0.66
    BIBLIOGRAPHY
    -0.63
     Lastly
    -0.59
    Παραπομπές
    -0.58
     sometimes
    -0.58
     eventually
    -0.57
    POSITIVE LOGITS
    TagMode
    0.72
    SourceChecksum
    0.67
    EndGlobalSection
    0.59
    setVerticalGroup
    0.56
    例文帳に追加
    0.56
     Athenian
    0.56
       
    0.55
     Certo
    0.55
     ་་
    0.54
     Cæsar
    0.53
    Activations Density 0.259%

    No Known Activations