Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 7800
    Prev
    Next
    INDEX
    Explanations

    key terms related to medical conditions, diagnostics, and environmental health impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/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.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ียน
    -0.56
    dited
    -0.50
     ActionListener
    -0.49
     Bow
    -0.47
     MediatR
    -0.45
     dự
    -0.44
    énier
    -0.44
     Lead
    -0.43
    heta
    -0.43
     lead
    -0.42
    POSITIVE LOGITS
    ConstraintMaker
    1.01
    CloseOperation
    0.91
     surla
    0.85
    Personensuche
    0.84
    expandindo
    0.81
    WriteBarrier
    0.77
     ویکی‌پدیا
    0.75
     createSprite
    0.75
    ScopeManager
    0.69
     دیکھیے
    0.69
    Activations Density 2.682%

    No Known Activations