© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 28481
    Prev
    Next
    INDEX
    Explanations

    demographic information, specifically population statistics of locations

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

    population density

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hasMoreElements
    -0.52
     ModelExpression
    -0.50
     esternos
    -0.50
    دانشنامهٔ
    -0.50
    utsal
    -0.49
    ibili
    -0.49
    oss
    -0.49
    flink
    -0.48
     Equip
    -0.48
     involving
    -0.47
    POSITIVE LOGITS
     population
    0.83
    population
    0.76
     habitants
    0.74
     living
    0.73
     inhabitants
    0.71
     POPULATION
    0.70
    Demographics
    0.68
    人口
    0.68
     Population
    0.67
    Population
    0.66
    Activations Density 0.070%

    No Known Activations