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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 93364
    Prev
    Next
    INDEX
    Explanations

    terms related to geography and spatial characteristics

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

    geographic location and area

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     ExecuteAsync
    -0.50
     الرياضيه
    -0.46
    *~*~
    -0.46
    참고
    -0.46
    preven
    -0.45
    Itz
    -0.45
    parsedMessage
    -0.44
     initState
    -0.44
     Untold
    -0.43
    ρισσότε
    -0.42
    POSITIVE LOGITS
     geographic
    1.06
     geography
    1.02
     Geography
    0.99
     geographical
    0.98
     Geographic
    0.97
    Geography
    0.96
    Geographic
    0.93
     geograph
    0.93
    geographic
    0.91
     geogra
    0.87
    Activations Density 0.004%

    No Known Activations