© 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. 38-GEMMASCOPE-RES-16K
    11. 13328
    Prev
    Next
    INDEX
    Explanations

    references to individuals and their roles or activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dítě
    -0.71
     dům
    -0.69
     místě
    -0.67
     zboží
    -0.67
     řek
    -0.66
     světě
    -0.65
     řízení
    -0.65
     dezelve
    -0.64
     místa
    -0.64
     zaměst
    -0.64
    POSITIVE LOGITS
     Czech
    1.19
    Czech
    0.94
     Prague
    0.91
     Czechoslovak
    0.84
     Brno
    0.77
    Prague
    0.75
     Cze
    0.74
     Slovak
    0.71
     CZ
    0.71
     Praha
    0.71
    Activations Density 0.111%

    No Known Activations