© 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. 4410
    Prev
    Next
    INDEX
    Explanations

    various types of function call syntax in code snippets

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

    Code containing parentheses

    np_acts-logits-general · gemini-2.0-flash

    code punctuation and 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
     kebaikan
    -0.43
    kind
    -0.43
    Гео
    -0.40
    ље
    -0.40
     Hernando
    -0.39
    b
    -0.39
    Мекси
    -0.39
    渝
    -0.39
     viață
    -0.39
    xi
    -0.39
    POSITIVE LOGITS
    IUrlHelper
    0.85
    KommentareTeilen
    0.77
    Personendaten
    0.77
    Jeografia
    0.72
    InjectAttribute
    0.69
     >=",
    0.68
     autorytatywna
    0.65
    hoeddwyd
    0.65
     console
    0.65
    viewDidLoad
    0.64
    Activations Density 0.037%

    No Known Activations