© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3310
    Prev
    Next
    INDEX
    Explanations

    elements related to statistical analysis and plotting results

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

    figures containing plots or graphs

    np_acts-logits-general · gemini-2.0-flash

    graphs, plots, and charts

    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
    interopRequire
    -0.56
    ⋙
    -0.48
     coscienza
    -0.48
    brainly
    -0.46
     înd
    -0.45
     pesante
    -0.44
     matière
    -0.44
     calcetines
    -0.44
    complexType
    -0.44
    ্প
    -0.43
    POSITIVE LOGITS
     graph
    1.93
     graphs
    1.92
     plot
    1.87
     plots
    1.82
    plot
    1.66
     Plot
    1.58
     plotted
    1.55
     charts
    1.54
     Graphs
    1.52
     Graph
    1.52
    Activations Density 1.490%

    No Known Activations