© 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. 20-GEMMASCOPE-RES-16K
    11. 11188
    Prev
    Next
    INDEX
    Explanations

    specific geographic locations within Alaska

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

    Alaska, especially place names

    np_acts-logits-general · gemini-2.0-flash

    Alaska cities and locations

    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
    •Gemma cluster 5

    No Comments

    Negative Logits
     resourceCulture
    -0.65
     Monmouth
    -0.61
     Lodi
    -0.58
     Leicestershire
    -0.58
     Ronnie
    -0.54
    Maharashtra
    -0.52
     Burundi
    -0.52
    recated
    -0.51
     Worcestershire
    -0.51
     Maharashtra
    -0.50
    POSITIVE LOGITS
     Alaska
    1.30
     Alaskan
    1.13
    Alaska
    1.13
     alaska
    1.01
     Anchorage
    0.98
     Fairbanks
    0.96
     Juneau
    0.88
    alaska
    0.88
     tundra
    0.81
    Anch
    0.77
    Activations Density 0.185%

    No Known Activations