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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 3-GEMMASCOPE-RES-16K
    6. 11128
    Prev
    Next
    INDEX
    Explanations

    statements that produce output in Java

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     intptr
    -0.63
    стоин
    -0.62
    øya
    -0.60
    はじめに
    -0.60
     चीज़ों
    -0.59
    qrstuvwxyz
    -0.59
    voyance
    -0.56
    )];
    
    -0.56
    "]));
    -0.55
     disponibilità
    -0.55
    POSITIVE LOGITS
    out
    1.27
     GoogleFonts
    0.78
     javafx
    0.77
    printStackTrace
    0.76
    Out
    0.75
     defaultstate
    0.72
     actionPerformed
    0.71
    dotenv
    0.71
    OUT
    0.71
    Mockito
    0.70
    Activations Density 0.030%

    No Known Activations