© 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. 13366
    Prev
    Next
    INDEX
    Explanations

    topics related to urban development and population dynamics

    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
     familiare
    -0.50
     cappuccio
    -0.47
    angan
    -0.44
     agarose
    -0.44
     familiari
    -0.44
    łoś
    -0.43
    agissait
    -0.43
    aide
    -0.43
     suspe
    -0.43
     unità
    -0.43
    POSITIVE LOGITS
     trend
    1.05
     future
    1.03
     emerging
    0.94
     trends
    0.94
    future
    0.93
    これから
    0.87
     increasingly
    0.86
    今後
    0.82
     demand
    0.81
     Trends
    0.81
    Activations Density 0.384%

    No Known Activations