© 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. 34-GEMMASCOPE-RES-16K
    11. 11668
    Prev
    Next
    INDEX
    Explanations

    geographical or location-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mon
    -0.36
     본
    -0.34
     Florida
    -0.33
     informée
    -0.32
     Maharashtra
    -0.31
     Santorini
    -0.30
     Bradford
    -0.30
     seguro
    -0.29
     cup
    -0.28
    aph
    -0.28
    POSITIVE LOGITS
     Kazakhstan
    0.89
    Kazakhstan
    0.77
     Kaz
    0.77
    Personensuche
    0.71
    Kaz
    0.67
    IsMutable
    0.66
     kaz
    0.65
    KZ
    0.63
     kazak
    0.61
     Nazar
    0.61
    Activations Density 0.094%

    No Known Activations