© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 151
    Prev
    Next
    INDEX
    Explanations

    references to locations, particularly cities and regions, especially in Washington state

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    Locations in Washington state

    np_acts-logits-general · gemini-2.0-flash

    Seattle and Pacific Northwest cities

    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
    Negative Logits
     Kildare
    -0.72
     cubanos
    -0.71
     Zimbabwe
    -0.71
     Cuban
    -0.70
     Barbados
    -0.70
     Yoruba
    -0.69
    Barbados
    -0.68
     Villanova
    -0.65
    Zimbabwe
    -0.64
    Nassau
    -0.64
    POSITIVE LOGITS
     Seattle
    2.21
    Seattle
    2.00
     Puget
    1.65
     Spokane
    1.65
    seattle
    1.61
     Oregon
    1.58
     Tacoma
    1.50
    Oregon
    1.45
     Vancouver
    1.37
     Pacific
    1.35
    Activations Density 0.219%

    No Known Activations