© 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. 3-GEMMASCOPE-RES-16K
    11. 6786
    Prev
    Next
    INDEX
    Explanations

    terms related to health, safety, and well-being

    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
    ".
    -0.99
     Efq
    -0.94
    )");
    -0.92
     betweenstory
    -0.90
     fevere
    -0.89
    .",
    -0.87
    "]);
    -0.87
    \"",
    -0.86
    "])
    -0.85
    ."));
    -0.84
    POSITIVE LOGITS
    <bos>
    0.78
     térm
    0.68
    .
    0.56
     anglès
    0.56
     pères
    0.55
     prisonniers
    0.55
     battre
    0.54
     preuves
    0.54
     francès
    0.54
     sonno
    0.54
    Activations Density 3.283%

    No Known Activations