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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 9623
    Prev
    Next
    INDEX
    Explanations

    references to Swedish entities and organizations

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

    Sweden, Swedish, Swedes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ckså
    -0.36
    gräns
    -0.35
    ställning
    -0.35
    Grá
    -0.32
    multirow
    -0.32
     гле
    -0.32
     barnen
    -0.31
    father
    -0.31
    hålla
    -0.30
     gräns
    -0.29
    POSITIVE LOGITS
     autorytatywna
    0.86
    Sweden
    0.75
    SequentialGroup
    0.74
     Swedish
    0.73
     Sweden
    0.73
     schwed
    0.70
     swedish
    0.68
    Swedish
    0.68
     Swedes
    0.66
    himovic
    0.63
    Activations Density 0.161%

    No Known Activations