© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 46629
    Prev
    Next
    INDEX
    Explanations

    references to Spain and Spanish culture

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

    Spain and Spanish

    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
     otomatig
    -0.71
    protoimpl
    -0.70
    BeginContext
    -0.70
    makeConstraints
    -0.69
    addCriterion
    -0.67
    writeField
    -0.65
    \}\\
    -0.62
    Билгалдахарш
    -0.61
    parsedMessage
    -0.60
    InjectMocks
    -0.59
    POSITIVE LOGITS
     Spain
    1.05
    Spain
    0.99
     Spanish
    0.82
     Espanha
    0.80
    pañol
    0.80
     Spanien
    0.79
     España
    0.75
     Spanyol
    0.74
    Spanish
    0.74
     española
    0.71
    Activations Density 0.006%

    No Known Activations