© 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-2-9B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 5165
    Prev
    Next
    INDEX
    Explanations

    names of Hungarian individuals, particularly in contexts related to mathematics or diving

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     panoramique
    -0.54
     polaire
    -0.54
     segíts
    -0.53
     creș
    -0.49
    ostante
    -0.47
     abstrait
    -0.47
     saurait
    -0.46
    ToRefresh
    -0.45
     politiet
    -0.45
    OCCURRED
    -0.45
    POSITIVE LOGITS
    Hozzáférés
    0.79
    Források
    0.57
    Jegyzetek
    0.56
     للاسماء
    0.53
     Sod
    0.47
     Hungarian
    0.46
     Hungary
    0.46
    __':
    0.44
    Hungary
    0.43
     Zol
    0.43
    Activations Density 0.146%

    No Known Activations