© 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. 3-GEMMASCOPE-RES-16K
    11. 1432
    Prev
    Next
    INDEX
    Explanations

    terms related to deficiencies and regulations in biological or medical contexts

    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
     gently
    -0.58
     exactly
    -0.55
     clearly
    -0.54
     easily
    -0.53
     Gently
    -0.53
     essentially
    -0.52
     truly
    -0.52
     quietly
    -0.52
     fraî
    -0.50
     doucement
    -0.50
    POSITIVE LOGITS
    StoryboardSegue
    0.85
     بيها
    0.77
    UserScript
    0.75
    RectangleBorder
    0.75
    UrlResolution
    0.72
    তথ্যসূত্র
    0.70
    Hentet
    0.70
     Signalez
    0.68
     Normdatei
    0.67
    RenderAtEndOf
    0.67
    Activations Density 0.573%

    No Known Activations