© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 6989
    Prev
    Next
    INDEX
    Explanations

    specific locations or settings associated with physical items or gatherings

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

    references to furniture and specific furniture items.

    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
     nocturna
    -0.39
    
    -0.38
     foton
    -0.38
    properties
    -0.38
     sûr
    -0.37
    urança
    -0.37
    ventude
    -0.37
    ApplicationTests
    -0.36
     condición
    -0.36
    IonicModule
    -0.35
    POSITIVE LOGITS
     desk
    0.75
     desks
    0.68
     للاسماء
    0.61
    desk
    0.60
     dresser
    0.60
     altar
    0.60
     chair
    0.57
     floor
    0.57
     table
    0.56
     sofa
    0.56
    Activations Density 0.114%

    No Known Activations