© 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. 6406
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to scientific research, particularly in biological and medical contexts

    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
     vestiti
    -0.73
    CompilerServices
    -0.69
     sogni
    -0.68
     abstrait
    -0.65
     égal
    -0.64
     mourir
    -0.64
    FirebaseDatabase
    -0.62
     cervello
    -0.62
    WebServlet
    -0.61
     "'");
    -0.61
    POSITIVE LOGITS
    complexContent
    0.90
    NameInMap
    0.82
     GBIF
    0.66
    :✨
    0.62
    لیس
    0.61
     confor
    0.60
     cleave
    0.59
     relevantes
    0.58
    WebElement
    0.57
     timelines
    0.56
    Activations Density 3.928%

    No Known Activations