© 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-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 6398
    Prev
    Next
    INDEX
    Explanations

    references to locations within Michigan, particularly cities and townships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hysema
    -0.67
     vastaan
    -0.64
    wahati
    -0.64
    ãy
    -0.60
     Bristol
    -0.59
     Bern
    -0.58
     gră
    -0.56
     QWidget
    -0.55
    Bristol
    -0.54
    orable
    -0.53
    POSITIVE LOGITS
     Detroit
    1.43
    Detroit
    1.33
     Michigan
    1.32
    Michigan
    1.25
     MICHIGAN
    1.13
     DETROIT
    1.11
     Wolver
    0.95
    higan
    0.95
    ROIT
    0.91
    detroit
    0.91
    Activations Density 0.534%

    No Known Activations