© 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-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 8771
    Prev
    Next
    INDEX
    Explanations

    references to files and their characteristics in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monfieur
    -1.14
    XtraReports
    -1.08
     متعلقه
    -1.02
    NameInMap
    -1.01
     reaſon
    -1.00
     تضيفلها
    -0.97
     &___
    -0.95
     Chriftian
    -0.94
     Efq
    -0.93
     ſeveral
    -0.90
    POSITIVE LOGITS
     file
    1.65
     files
    1.50
     File
    1.46
     getFile
    1.26
    File
    1.25
     FILE
    1.25
    file
    1.21
    files
    1.18
    Files
    1.15
     Files
    1.14
    Activations Density 0.094%

    No Known Activations