© 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. 3674
    Prev
    Next
    INDEX
    Explanations

    phrases related to coding or programming syntax

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

    "using" keyword in C# or similar coding languages

    np_acts-logits-general · gemini-2.0-flash

    C# using statements

    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
     vaid
    -0.50
     Voyez
    -0.47
    IntoConstraints
    -0.45
     uſed
    -0.43
    spół
    -0.43
     alſo
    -0.42
     AttributeError
    -0.42
     pinky
    -0.41
     pezzo
    -0.41
    prechen
    -0.40
    POSITIVE LOGITS
     Microsoft
    0.88
    
    0.82
    Datuak
    0.82
    зулта
    0.81
     System
    0.79
     Савезне
    0.79
    |')
    0.76
    DoubleQuotes
    0.76
     autorytatywna
    0.76
    namespace
    0.74
    Activations Density 0.027%

    No Known Activations