© 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. 20-GEMMASCOPE-RES-16K
    11. 11709
    Prev
    Next
    INDEX
    Explanations

    technical terms and jargon related to data processing and analysis

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

    Preceding "before," "the," or a measurement

    np_acts-logits-general · gemini-2.0-flash

    American television and writing categories

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    TagMode
    -0.82
    Personendaten
    -0.70
    ArgsConstructor
    -0.69
    EndGlobalSection
    -0.69
    __':
    -0.66
    msgSender
    -0.66
    fjspx
    -0.65
    DeleteMapping
    -0.62
    ThroughAttribute
    -0.62
     useAppContext
    -0.61
    POSITIVE LOGITS
     ditto
    0.91
    ditto
    0.76
    則是
    0.71
    则是
    0.69
    StructEnd
    0.67
    同じく
    0.64
     invece
    0.63
     likewise
    0.61
    又是
    0.57
    帖最后由
    0.55
    Activations Density 4.839%

    No Known Activations