© 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. 3840
    Prev
    Next
    INDEX
    Explanations

    technical terms and code snippets related to geographic information systems (GIS)

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

    Geographic Information Systems (GIS) layers

    np_acts-logits-general · gemini-2.0-flash

    WMS layers and spatial references

    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
    FontOfSize
    -0.55
     bran
    -0.54
    Vidite
    -0.53
    ANTLR
    -0.51
    glfw
    -0.51
    querque
    -0.51
    hoga
    -0.50
    EditorBrowsable
    -0.50
    restle
    -0.48
    contentLoaded
    -0.48
    POSITIVE LOGITS
     spatial
    0.80
    layer
    0.78
     Spatial
    0.77
     layer
    0.76
    Spatial
    0.75
    spatial
    0.73
    Layer
    0.73
    Feature
    0.71
     layers
    0.69
     raster
    0.69
    Activations Density 0.169%

    No Known Activations