© 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. 40-GEMMASCOPE-RES-16K
    11. 5814
    Prev
    Next
    INDEX
    Explanations

    discussions of societal issues and events, particularly those related to economics, justice, and political conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    delwed
    -0.54
    piecze
    -0.50
    makeConstraints
    -0.47
    Havolalar
    -0.47
     Italijanski
    -0.46
    tagHelperRunner
    -0.44
    endpush
    -0.44
     Biôgrafia
    -0.43
     المعيارى
    -0.43
     kohdetta
    -0.42
    POSITIVE LOGITS
     happening
    1.65
     taking
    1.46
     occurring
    1.38
     unfolding
    1.30
    happ
    1.17
     going
    1.15
    Taking
    1.11
    taking
    1.10
     Taking
    1.09
     underway
    1.06
    Activations Density 0.643%

    No Known Activations