© 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. 2547
    Prev
    Next
    INDEX
    Explanations

    code syntax related to type checking and instantiation in programming languages

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

    Code related to classes or types

    np_acts-logits-general · gemini-2.0-flash

    class and type contexts

    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
    ские
    -0.45
    HtmlAttribute
    -0.41
     notare
    -0.41
     Setting
    -0.40
    苷
    -0.39
     emporter
    -0.39
     
    -0.39
    akhstan
    -0.39
    XmlAttribute
    -0.39
    ازی
    -0.39
    POSITIVE LOGITS
    Class
    1.05
    getClass
    1.01
     Class
    1.00
     clazz
    0.94
     typeof
    0.92
     class
    0.91
     getClass
    0.86
    typeof
    0.86
     classes
    0.85
    QMetaType
    0.85
    Activations Density 0.310%

    No Known Activations