© 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. 15890
    Prev
    Next
    INDEX
    Explanations

    the presence of opening brackets or parentheses

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

    LaTeX code snippets

    np_acts-logits-general · gemini-2.0-flash

    LaTeX and TikZ syntax

    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
    sste
    -0.47
     verf
    -0.43
    mouseleave
    -0.43
    InstanceState
    -0.42
     kle
    -0.40
    ney
    -0.40
    dika
    -0.39
     gewe
    -0.38
     Deal
    -0.38
     ineff
    -0.37
    POSITIVE LOGITS
     Италијани
    0.95
    Autoritní
    0.87
    expandindo
    0.78
    protoimpl
    0.67
     Administrativna
    0.67
     للاسماء
    0.64
     rêver
    0.64
    Suara
    0.64
     Савезне
    0.63
    UrlResolution
    0.62
    Activations Density 0.047%

    No Known Activations