© 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. 37-GEMMASCOPE-RES-16K
    11. 1510
    Prev
    Next
    INDEX
    Explanations

    names of Bollywood celebrities and their associations with fashion events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     newBuilder
    -0.43
     człowie
    -0.37
     Moisés
    -0.34
     domov
    -0.34
     Rheinland
    -0.33
     domestique
    -0.32
     household
    -0.32
    ţe
    -0.31
    uvres
    -0.31
    语法
    -0.31
    POSITIVE LOGITS
    RegressionTest
    0.89
     INTERESAR
    0.67
    SharedDtor
    0.67
    AsUp
    0.58
     TextAppearance
    0.57
    Rite
    0.57
    ruptedException
    0.56
    WriteLiteral
    0.55
    ArrowToggle
    0.54
    SequentialGroup
    0.54
    Activations Density 0.184%

    No Known Activations