© 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. 3883
    Prev
    Next
    INDEX
    Explanations

    references to metropolitan areas and their geographic locations

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

    preceding regions/areas of places

    np_acts-logits-general · gemini-2.0-flash

    geographic regions and municipalities

    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
     ModelExpression
    -0.71
    httphttps
    -0.71
    GEBURTSDATUM
    -0.66
    Personendaten
    -0.62
    GOTREF
    -0.57
    bootstrapcdn
    -0.56
    }(),
    -0.56
    __);
    -0.56
    ]")]
    -0.56
     MainAxisSize
    -0.55
    POSITIVE LOGITS
     Greater
    1.28
    Greater
    1.07
     greater
    1.07
     metro
    1.04
    greater
    1.03
     region
    0.97
     area
    0.97
     Metro
    0.96
     metropolitan
    0.91
    metro
    0.87
    Activations Density 0.210%

    No Known Activations