© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 10138
    Prev
    Next
    INDEX
    Explanations

    elements related to cultural and culinary characteristics

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

    Nationalities or origins of people or things

    np_acts-logits-general · gemini-2.0-flash

    nationalities and regions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rígido
    -0.46
     Baumwolle
    -0.44
     hidráulica
    -0.44
     manifiesto
    -0.43
    trás
    -0.43
    hadiran
    -0.42
     faldas
    -0.42
     Vereinbarung
    -0.42
     gruesa
    -0.42
    unanje
    -0.41
    POSITIVE LOGITS
     Canadian
    0.73
     British
    0.66
    +#+#
    0.62
     American
    0.61
     UK
    0.60
    hyrchwyd
    0.60
     Aussie
    0.60
     European
    0.59
     Israeli
    0.59
     Texan
    0.59
    Activations Density 1.312%

    No Known Activations