© 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. 5075
    Prev
    Next
    INDEX
    Explanations

    references to wetlands and their characteristics, particularly in relation to marsh harriers and their habitats

    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
    ViewImports
    -0.52
     Kích
    -0.46
     Infórmanos
    -0.44
    OfYear
    -0.44
    stdafx
    -0.40
    ScopeManager
    -0.40
    bcryptjs
    -0.39
     Machu
    -0.39
    kembangan
    -0.39
     núi
    -0.39
    POSITIVE LOGITS
     wetland
    0.72
     Wetlands
    0.68
     wetlands
    0.68
     Wetland
    0.65
     marsh
    0.61
     swamp
    0.58
     duck
    0.56
    swamp
    0.55
     marshes
    0.55
     Swamp
    0.54
    Activations Density 0.619%

    No Known Activations