© 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-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 3444
    Prev
    Next
    INDEX
    Explanations

    recommendations or suggestions for must-see films, books, and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/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.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyProduct
    -0.97
    AccessorTable
    -0.89
    titleMargin
    -0.86
     MessageBoxIcon
    -0.83
    transQ
    -0.80
    MigrationBuilder
    -0.79
    
    -0.78
     protoimpl
    -0.75
    ServletConfig
    -0.75
     betweenstory
    -0.75
    POSITIVE LOGITS
     must
    1.50
    must
    1.40
     MUST
    1.39
     Must
    1.35
    Must
    1.30
    MUST
    1.17
    一定要
    1.01
     unbedingt
    1.00
     wajib
    0.97
     definitely
    0.95
    Activations Density 0.107%

    No Known Activations