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

    Neuronpedia

    Jacobian LensNEW
    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. 21-GEMMASCOPE-RES-16K
    11. 5659
    Prev
    Next
    INDEX
    Explanations

    class and interface declarations in programming code, specifically in Java and Kotlin

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/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.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -0.77
    "](
    -0.71
    numerusform
    -0.71
    发表于
    -0.65
    .";
    -0.63
    ("}");
    -0.63
    ".
    -0.63
    "]);
    -0.62
     Sinon
    -0.61
    ")"
    -0.61
    POSITIVE LOGITS
     implements
    0.94
    implements
    0.71
    <?
    0.58
     implement
    0.52
     Pública
    0.50
     undertakes
    0.49
    /**
    0.48
     implementing
    0.48
    antaine
    0.48
    Implementing
    0.46
    Activations Density 0.048%

    No Known Activations