© 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. 24-GEMMASCOPE-RES-16K
    11. 10244
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to duchies and their governance

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

    Germanic/Scandinavian place names (Schleswig, Holstein, etc.)

    np_acts-logits-general · gemini-2.0-flash

    duchy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     leaſt
    -0.59
     ſeveral
    -0.56
     myſelf
    -0.53
     Efq
    -0.53
     firſt
    -0.52
     juſt
    -0.52
     Manag
    -0.51
     faſt
    -0.51
     uſed
    -0.51
     ſche
    -0.51
    POSITIVE LOGITS
     GenerationType
    0.83
     MainAxisSize
    0.72
    таратура
    0.68
     TextAppearance
    0.62
    onAttach
    0.57
    chtigkeit
    0.55
     оригіналу
    0.54
    ArrowToggle
    0.52
     luật
    0.51
     couverte
    0.51
    Activations Density 0.223%

    No Known Activations