© 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. 15950
    Prev
    Next
    INDEX
    Explanations

    patterns related to regular expressions and their syntax

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

    Code snippets with operators

    np_acts-logits-general · gemini-2.0-flash

    regular expressions and code constructs

    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
     
    -0.63
     –
    -0.49
    .
    -0.44
    -
    -0.43
     in
    -0.40
    ,
    -0.40
    <eos>
    -0.39
     respect
    -0.38
      
    -0.38
     -
    -0.38
    POSITIVE LOGITS
     .*
    0.94
    rungsseite
    0.89
     GoogleFonts
    0.89
     Administrativna
    0.88
    .*
    0.86
     ([
    0.84
    EDEFAULT
    0.84
     (?
    0.81
     Jefus
    0.80
     Efq
    0.79
    Activations Density 0.210%

    No Known Activations