© 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. 22-GEMMASCOPE-RES-16K
    11. 8509
    Prev
    Next
    INDEX
    Explanations

    names of locations, entities, and notable individuals related to U.S. politics and geography

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

    Comes before location names

    np_acts-logits-general · gemini-2.0-flash

    Super Bowl, Los Angeles, San Francisco

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -0.77
     marseille
    -0.63
     tuong
    -0.62
     onely
    -0.61
     Allegretto
    -0.60
     fhew
    -0.59
     Timoteo
    -0.59
     vnto
    -0.58
    США
    -0.58
     quæ
    -0.58
    POSITIVE LOGITS
     AssemblyCulture
    0.73
     Audiodateien
    0.70
    ruptedException
    0.70
    ReusableCell
    0.65
    TagMode
    0.64
     
    0.58
    HomeAsUpEnabled
    0.58
    
    0.57
     
    0.55
    testens
    0.54
    Activations Density 0.605%

    No Known Activations