© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 10-GEMMASCOPE-RES-16K
    11. 5451
    Prev
    Next
    INDEX
    Explanations

    references to file formats and operations related to importing, exporting, and saving files in various formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/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.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
     architecture
    -0.42
     ARCHITECTURE
    -0.39
     architectural
    -0.39
    architecture
    -0.38
     toros
    -0.37
     Architecture
    -0.36
     architectures
    -0.36
     Acción
    -0.35
     genetic
    -0.35
     Architectural
    -0.35
    POSITIVE LOGITS
    TagMode
    0.89
     nahilalakip
    0.84
    BeginContext
    0.72
    bootstrapcdn
    0.69
     autorytatywna
    0.66
     '\\;'
    0.62
    出版年
    0.62
    CodeDom
    0.61
    SaveChangesAsync
    0.60
     detailsLots
    0.59
    Activations Density 0.503%

    No Known Activations