© 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. 41-GEMMASCOPE-RES-16K
    6. 8193
    Prev
    Next
    INDEX
    Explanations

    references to tourism and activities in a specific location

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ANTLR
    -0.56
    OGND
    -0.54
    ècie
    -0.47
    dyž
    -0.44
     franqu
    -0.43
     skär
    -0.43
     للمعارف
    -0.41
    ScopeManager
    -0.41
    tabControl
    -0.41
     StatefulWidget
    -0.41
    POSITIVE LOGITS
     transfer
    0.98
     Transfer
    0.94
     transfers
    0.92
    Transfer
    0.90
     Transfers
    0.89
    transfers
    0.86
    transfer
    0.86
    Transfers
    0.82
     TRANSFER
    0.80
     transfert
    0.76
    Activations Density 0.124%

    No Known Activations