© 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. 664
    Prev
    Next
    INDEX
    Explanations

    connections to family lineage and relationships

    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
    varargin
    -0.50
     BoxFit
    -0.44
    addContainerGap
    -0.42
    PropertyGroup
    -0.42
    BoxShadow
    -0.41
    ClientRect
    -0.40
    licet
    -0.40
    salle
    -0.40
    geer
    -0.39
    ochim
    -0.39
    POSITIVE LOGITS
     infant
    0.90
    infant
    0.81
     Infant
    0.73
    Infant
    0.71
     infants
    0.58
     infancy
    0.56
     baby
    0.53
    MigrationBuilder
    0.51
     newborn
    0.51
     bébés
    0.51
    Activations Density 0.142%

    No Known Activations