© 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. 8-GEMMASCOPE-RES-16K
    11. 198
    Prev
    Next
    INDEX
    Explanations

    distinct scientific or technical terms related to biology, physics, and law

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     partea
    -0.77
     considérée
    -0.70
     démission
    -0.69
     venait
    -0.68
     binoculars
    -0.68
     anaknya
    -0.67
     aquilo
    -0.67
     geologists
    -0.67
     is
    -0.66
     auxquelles
    -0.66
    POSITIVE LOGITS
    fible
    1.09
    )";
    1.08
    '},
    1.07
    []
    1.06
    )");
    1.06
     $_"
    1.03
    ")));
    1.03
    ".
    1.02
    ^(@)
    1.02
    &
    1.01
    Activations Density 5.311%

    No Known Activations