© 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. 10954
    Prev
    Next
    INDEX
    Explanations

    references to news articles and categories

    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
    pośred
    -0.41
     toalha
    -0.39
     thiệu
    -0.38
     médaille
    -0.36
     comunicarse
    -0.35
    Wymiary
    -0.35
    wska
    -0.34
     elástica
    -0.34
     الإعلام
    -0.34
    Marking
    -0.33
    POSITIVE LOGITS
     lifestyle
    0.96
     Lifestyle
    0.93
     sports
    0.93
     entertainment
    0.91
    Lifestyle
    0.87
     Entertainment
    0.85
     Sports
    0.81
    lifestyle
    0.81
     sport
    0.80
    Entertainment
    0.80
    Activations Density 0.354%

    No Known Activations