© 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. 20-GEMMASCOPE-RES-16K
    11. 4025
    Prev
    Next
    INDEX
    Explanations

    parentheses and other delimiters often used in mathematical or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Characters commonly used in math or code

    np_acts-logits-general · gemini-2.0-flash

    Opening brackets and specific symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.80
    nexo
    -0.69
     General
    -0.67
      
    -0.63
     L
    -0.61
     Иль
    -0.59
     E
    -0.59
     g
    -0.57
     }
    -0.57
     G
    -0.57
    POSITIVE LOGITS
     للمعارف
    1.39
    SequentialGroup
    1.09
     AssemblyTitle
    0.97
     ExecuteAsync
    0.97
     bershka
    0.96
     myſelf
    0.96
    (!__
    0.94
     contextLoads
    0.94
     Phry
    0.94
     moschino
    0.93
    Activations Density 0.487%

    No Known Activations