© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 44024
    Prev
    Next
    INDEX
    Explanations

    names of locations, particularly states and cities in the United States

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

    US state abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     चीज़ों
    -0.96
    uxxxx
    -0.84
    
    -0.81
    лтемелер
    -0.78
     surla
    -0.73
    hyrchwyd
    -0.72
     nahilalakip
    -0.71
    :✨
    -0.71
     Taktlose
    -0.70
    AsUp
    -0.70
    POSITIVE LOGITS
     
    0.57
    ,
    0.38
      
    0.36
    [
    0.33
    -
    0.33
      
    0.32
            
    0.31
    und
    0.31
     –
    0.30
     royaume
    0.30
    Activations Density 0.010%

    No Known Activations