© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 11320
    Prev
    Next
    INDEX
    Explanations

    references to programming languages and libraries, particularly in Java and Android

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

    Code snippets containing "java"

    np_acts-logits-general · gemini-2.0-flash

    java or javax code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lat
    -0.54
    äd
    -0.53
    NOTA
    -0.51
     cut
    -0.49
    ؤلاء
    -0.48
     =>
    -0.48
    σίας
    -0.47
    UNCIL
    -0.47
    ducted
    -0.46
     defra
    -0.46
    POSITIVE LOGITS
    isContained
    0.90
     nakalista
    0.83
    Datuak
    0.78
     ExecuteAsync
    0.77
    ंदीखरीदारी
    0.75
     المعيارى
    0.73
     >=",
    0.69
     مرئيه
    0.69
    Gemeinden
    0.67
     snippetHide
    0.66
    Activations Density 0.034%

    No Known Activations