© 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. 20-GEMMASCOPE-RES-16K
    11. 1190
    Prev
    Next
    INDEX
    Explanations

    topics related to tropical regions and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to tropical regions and environments.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     badger
    -0.66
    RenderAtEndOf
    -0.65
     MainAxisSize
    -0.64
    yntaxException
    -0.63
     AssemblyCompany
    -0.63
    orexia
    -0.60
     ſind
    -0.59
    ashqai
    -0.59
    ukone
    -0.59
     onOptions
    -0.59
    POSITIVE LOGITS
     tropical
    1.11
     Tropical
    0.97
     tropicales
    0.96
     tropics
    0.93
     Caribbean
    0.91
    Tropical
    0.90
    tropical
    0.87
    Caribbean
    0.79
     TROP
    0.75
     coconut
    0.72
    Activations Density 0.359%

    No Known Activations