© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 6459
    Prev
    Next
    INDEX
    Explanations

    the presence of specific medical terminology related to muscular degeneration and disease

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 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
     للاسماء
    -0.94
    ResponseWriter
    -0.86
    queryInterface
    -0.83
    reportWebVitals
    -0.81
    consulté
    -0.80
    EndGlobalSection
    -0.78
    ergies
    -0.78
    #
    -0.76
     Phaser
    -0.76
    Unmarshaller
    -0.74
    POSITIVE LOGITS
     nhật
    0.47
    вест
    0.44
     désol
    0.44
     humaines
    0.43
     intégrée
    0.43
    Извест
    0.42
     trás
    0.41
    subsubsection
    0.40
     pisau
    0.39
    授
    0.38
    Activations Density 0.312%

    No Known Activations