© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 9199
    Prev
    Next
    INDEX
    Explanations

    geographic locations and associated landmarks

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

    Locations, especially suburban areas/cities

    np_acts-logits-general · gemini-2.0-flash

    suburban and urban places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    ViewImports
    -0.55
    :✨
    -0.50
     endblock
    -0.50
    adaptiveStyles
    -0.49
    ngths
    -0.47
     nonUne
    -0.46
    jspb
    -0.45
    tagHelperRunner
    -0.44
     endforeach
    -0.43
    %</
    -0.43
    POSITIVE LOGITS
     suburban
    0.82
     Suburban
    0.68
     suburb
    0.62
     suburbs
    0.60
     Bekasi
    0.54
     Autobahn
    0.51
     Tangerang
    0.50
     Westchester
    0.50
     commuter
    0.49
     shopping
    0.48
    Activations Density 0.256%

    No Known Activations