© 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
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 14143
    Prev
    Next
    INDEX
    Explanations

    Spanish-language media references and entities

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

    references to Hispanic, Latino, and Spanish-language demographics, media, and cultural topics.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    majánló
    -1.06
     myſelf
    -0.98
     hadas
    -0.96
     Gonçalves
    -0.96
     desmotivaciones
    -0.95
     Araújo
    -0.94
     Milán
    -0.94
    ðsíða
    -0.93
     Monfieur
    -0.88
     Guimarães
    -0.87
    POSITIVE LOGITS
     Mexican
    0.71
     Мекси
    0.66
     Latin
    0.66
    Mexican
    0.59
     Hispanic
    0.57
     Mexico
    0.54
    Latin
    0.53
    墨西哥
    0.53
    멕
    0.51
    Mexico
    0.48
    Activations Density 0.773%

    No Known Activations