Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 4205
    Prev
    Next
    INDEX
    Explanations

    locations and proper nouns, particularly those associated with Seattle

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Zimbabwe
    -0.95
     Barbados
    -0.86
    Zimbabwe
    -0.84
     Cuban
    -0.83
     Trinidad
    -0.81
    Barbados
    -0.81
     cubanos
    -0.78
     Bermuda
    -0.77
     cubana
    -0.76
     Bahamas
    -0.76
    POSITIVE LOGITS
     Seattle
    2.19
    Seattle
    1.99
     Puget
    1.75
     Tacoma
    1.65
    seattle
    1.62
     Washington
    1.53
     Spokane
    1.44
    Washington
    1.41
     Yakima
    1.38
     Seahawks
    1.36
    Activations Density 0.350%

    No Known Activations