© 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 EvalsExportsinterp-engineNEWAPI 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. 7304
    Prev
    Next
    INDEX
    Explanations

    references to organizations, particularly those related to politics and governance

    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
     Parisian
    -0.64
    フレンチ
    -0.58
     Florentine
    -0.56
    namese
    -0.54
     اصفه
    -0.54
     Berliner
    -0.52
     Rican
    -0.51
     tartalomajánló
    -0.47
     روسی
    -0.47
    Egyptian
    -0.46
    POSITIVE LOGITS
     India
    1.88
     Italy
    1.82
     Ireland
    1.81
     Germany
    1.79
     Australia
    1.75
     Canada
    1.75
     Nigeria
    1.74
     France
    1.73
     Spain
    1.71
     Indonesia
    1.65
    Activations Density 1.576%

    No Known Activations