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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13084
    Prev
    Next
    INDEX
    Explanations

    references to locations, particularly related to the Seattle area and its vicinity

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

    Washington State locations

    np_acts-logits-general · gemini-2.0-flash

    Washington state cities

    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
    Nassau
    -0.60
    RegressionTest
    -0.58
    WithTag
    -0.56
     Reverso
    -0.55
    PANY
    -0.55
     Chwiliwch
    -0.55
    rimidine
    -0.55
    jedis
    -0.54
    $_['
    -0.54
     Lauder
    -0.53
    POSITIVE LOGITS
     Seattle
    1.49
    Seattle
    1.33
     Puget
    1.21
     Tacoma
    1.15
     Spokane
    1.08
    seattle
    1.05
     Yakima
    0.94
     Rainier
    0.90
     Bellingham
    0.89
     Sno
    0.87
    Activations Density 0.120%

    No Known Activations