© 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. 41-GEMMASCOPE-RES-16K
    11. 10699
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to a specific literary work or its themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kontra
    -0.34
     nabo
    -0.31
     nhung
    -0.29
     kompres
    -0.29
     sposo
    -0.28
     klima
    -0.27
     spille
    -0.27
     silikon
    -0.27
     temu
    -0.27
     fakt
    -0.27
    POSITIVE LOGITS
    featureID
    0.69
     ویکی‌پدی
    0.64
    EndGlobalSection
    0.62
    iſche
    0.60
     beſti
    0.59
     შ
    0.58
     ſeinem
    0.58
     незавершена
    0.58
     geweſen
    0.58
     სა
    0.57
    Activations Density 0.003%

    No Known Activations