© 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. 18-GEMMASCOPE-RES-16K
    11. 13525
    Prev
    Next
    INDEX
    Explanations

    mentions of locations, specifically focusing on references to Iowa and its cities

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

    Iowa and associated locations

    np_acts-logits-general · gemini-2.0-flash

    iowa and iowa locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddField
    -0.54
     forceps
    -0.52
    DeleteBehavior
    -0.49
    onOptions
    -0.48
     banho
    -0.48
     Harrell
    -0.47
     peruana
    -0.47
     calyx
    -0.47
    abstractmethod
    -0.44
    userdetails
    -0.43
    POSITIVE LOGITS
     Iowa
    1.25
    Iowa
    1.11
     IOWA
    1.06
     lowa
    0.94
     Moines
    0.92
     Hawkeye
    0.88
     StatelessWidget
    0.86
    iowa
    0.83
     Dubuque
    0.81
     StatefulWidget
    0.79
    Activations Density 0.103%

    No Known Activations