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

    Neuronpedia

    Jacobian LensNEW
    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. 24-GEMMASCOPE-RES-16K
    11. 7056
    Prev
    Next
    INDEX
    Explanations

    elements related to plotting data using colors and markers

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

    Matplotlib plotting and figures

    np_acts-logits-general · gemini-2.0-flash

    plt.plot

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Roskov
    -0.72
    :✨
    -0.72
    Personensuche
    -0.69
    Portály
    -0.68
    ThroughAttribute
    -0.67
     propOrder
    -0.63
    homonymie
    -0.63
    SourceChecksum
    -0.63
     disambiguazione
    -0.62
    GenerationType
    -0.59
    POSITIVE LOGITS
     figure
    1.08
     fig
    1.05
    fig
    1.02
    figure
    0.96
     Figure
    0.94
    plt
    0.92
     plt
    0.90
    Figure
    0.90
     figures
    0.88
     Fig
    0.83
    Activations Density 0.429%

    No Known Activations