© 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. 9025
    Prev
    Next
    INDEX
    Explanations

    occurrences of HTML-like angle brackets and their patterns

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

    Code snippets with generics/templates

    np_acts-logits-general · gemini-2.0-flash

    detected String objects

    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
     
    -1.03
     he
    -0.90
    .
    -0.88
     is
    -0.87
    ,
    -0.87
     to
    -0.87
     in
    -0.86
     of
    -0.83
     The
    -0.79
     A
    -0.78
    POSITIVE LOGITS
     myſelf
    1.81
     itſelf
    1.73
     Efq
    1.70
     Monfieur
    1.67
     auffi
    1.64
     purpoſe
    1.63
     pleaſure
    1.62
     poffible
    1.56
     Majefty
    1.55
     reaſon
    1.54
    Activations Density 0.054%

    No Known Activations