Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 6-GEMMASCOPE-RES-16K
    6. 9658
    Prev
    Next
    INDEX
    Explanations

    elements related to programming constructs, specifically in Java or similar languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     FetchType
    -0.79
    enterOuterAlt
    -0.58
    twimg
    -0.57
    CardContent
    -0.57
     protoimpl
    -0.56
     وتسجيلات
    -0.54
    SequentialGroup
    -0.52
    ią
    -0.52
    )?;
    -0.52
    <![
    -0.52
    POSITIVE LOGITS
     Baillargeon
    0.76
    Bibliograf
    0.71
     kaarangay
    0.63
    /*---
    0.62
    <bos>
    0.62
    хь
    0.59
     surla
    0.59
    ArrowToggle
    0.58
    kháu
    0.58
     supérieures
    0.58
    Activations Density 0.044%

    No Known Activations