© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 30-GEMMASCOPE-RES-16K
    6. 11091
    Prev
    Next
    INDEX
    Explanations

    geographical references, particularly related to borders and locations

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

    Locations bordering other locations

    np_acts-logits-general · gemini-2.0-flash

    contiguous regions or states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.56
     precinct
    -0.42
    Попис
    -0.38
    
    -0.36
     ExecuteAsync
    -0.36
    󠁬
    -0.36
     sodio
    -0.35
    bamos
    -0.35
    ‌شده
    -0.35
     Precinct
    -0.35
    POSITIVE LOGITS
     neighbouring
    0.61
     PeEnEo
    0.60
     border
    0.57
    Identyfik
    0.54
     neighboring
    0.54
     bordering
    0.54
     frontière
    0.50
    border
    0.49
    fohl
    0.49
     сосед
    0.49
    Activations Density 0.357%

    No Known Activations