© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 7268
    Prev
    Next
    INDEX
    Explanations

    references to significant events or situations relating to the FIFA World Cup

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

    FIFA and world cups

    np_acts-logits-general · gemini-2.0-flash

    FIFA World Cup

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    Personensuche
    -0.76
    ImageContext
    -0.73
    ⓧ
    -0.66
    Coordonnées
    -0.54
    homonymie
    -0.53
     ChromeDriver
    -0.52
    ixon
    -0.52
     Thackeray
    -0.52
    asantry
    -0.51
     препратки
    -0.51
    POSITIVE LOGITS
     FIFA
    0.87
    世界杯
    0.69
     Fifa
    0.69
     World
    0.69
     tournament
    0.68
     Mundial
    0.68
    FIFA
    0.63
     mundial
    0.60
     fifa
    0.58
    World
    0.58
    Activations Density 0.052%

    No Known Activations