© 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. 8978
    Prev
    Next
    INDEX
    Explanations

    statements about medical and scientific findings involving treatments or conditions

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

    Numbers (often less than ten)

    np_acts-logits-general · gemini-2.0-flash

    numerical counts

    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
    SequentialGroup
    -0.83
     kasarigan
    -0.81
     otomatig
    -0.75
    CloseOperation
    -0.75
    ViewImports
    -0.73
     Meksiku
    -0.72
     '\\;'
    -0.71
    存于互联网档案馆
    -0.71
     виправивши
    -0.70
     AssemblyCulture
    -0.68
    POSITIVE LOGITS
     four
    3.05
     five
    2.88
     six
    2.82
     three
    2.82
     seven
    2.68
     eight
    2.65
    four
    2.50
     nine
    2.48
    three
    2.36
     two
    2.33
    Activations Density 1.799%

    No Known Activations