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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 4674
    Prev
    Next
    INDEX
    Explanations

    significant architectural landmarks and their historical significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    museums or exhibits

    np_acts-logits-general · gemini-2.0-flash

    displays at museums

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PickerController
    -0.48
    netinet
    -0.45
    alei
    -0.45
     caractéris
    -0.45
    ync
    -0.45
    éditeur
    -0.44
     albicans
    -0.44
    ppincott
    -0.43
    ServiceProvider
    -0.43
     residuals
    -0.43
    POSITIVE LOGITS
     exhibits
    1.62
     exhibit
    1.52
     visitor
    1.45
     museum
    1.42
     exhibitions
    1.42
     visitors
    1.42
     Exhibits
    1.41
     displays
    1.39
     exhibition
    1.37
     Visitors
    1.32
    Activations Density 0.147%

    No Known Activations