© 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. 0-GEMMASCOPE-RES-16K
    11. 14768
    Prev
    Next
    INDEX
    Explanations

    specific formatting and symbol patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ویکی‌پدی
    -1.52
    rungsseite
    -1.50
     autorytatywna
    -1.40
     disambiguazione
    -1.37
    parsedMessage
    -1.31
     Италијани
    -1.29
    expandindo
    -1.27
     queſta
    -1.23
    setVerticalGroup
    -1.20
     للاسماء
    -1.19
    POSITIVE LOGITS
    ↵
    1.26
     
    1.16
      
    1.05
    ,
    1.02
    1
    0.94
     to
    0.90
     and
    0.90
     in
    0.88
     a
    0.87
     the
    0.86
    Activations Density 3.650%

    No Known Activations