© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 41-GEMMASCOPE-RES-16K
    11. 8555
    Prev
    Next
    INDEX
    Explanations

    mentions of construction, health, and economic conditions related to the United States and China

    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
     VIDEOTAPE
    -0.45
    macy
    -0.40
    graphique
    -0.39
    BufferException
    -0.39
     estekak
    -0.39
    DrawerToggle
    -0.39
    AdapterView
    -0.39
    AlterField
    -0.38
    ObjectContext
    -0.38
    Viitteet
    -0.38
    POSITIVE LOGITS
     economy
    1.14
    economy
    0.84
     economía
    0.66
     ECONOMY
    0.66
     Economy
    0.66
    Economy
    0.65
     workforce
    0.61
     économie
    0.60
    providedIn
    0.60
    économie
    0.58
    Activations Density 0.442%

    No Known Activations