© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15054
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and structures within the text

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

    LaTeX notation

    np_acts-logits-general · gemini-2.0-flash

    closing bracket or tag

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    Spoljašnje
    -0.79
    saraba
    -0.76
    aarrggbb
    -0.72
     Baillargeon
    -0.71
    الإنجليزية
    -0.64
     udaler
    -0.63
    AsUp
    -0.59
    InvalidProtocol
    -0.56
     EdgeInsets
    -0.54
    ToolStrip
    -0.53
    POSITIVE LOGITS
    انيف
    0.87
    </h5>
    0.69
    مصادر
    0.68
    0.65
    )$}
    0.65
    </sup>
    0.64
    </h3>
    0.63
    </h4>
    0.62
    >
    0.60
    0.59
    Activations Density 0.740%
    No Known Activations