© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 458
    Prev
    Next
    INDEX
    Explanations

    code structure and function definitions in programming contexts

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

    programming-related terms and concepts

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

    Java collections and data types

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     Funktion
    -0.58
     function
    -0.54
     lenker
    -0.51
     ***!
    -0.48
    関数
    -0.47
     함수
    -0.47
    ленную
    -0.46
    enterOuterAlt
    -0.46
    函数
    -0.45
     cannabis
    -0.45
    POSITIVE LOGITS
     java
    0.96
     {@
    0.89
     Java
    0.88
    java
    0.88
     bean
    0.85
     JVM
    0.83
    Java
    0.83
     JAXB
    0.80
    bean
    0.78
    {@
    0.77
    Activations Density 0.339%

    No Known Activations