© 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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15928
    Prev
    Next
    INDEX
    Explanations

    mentions of urban settings and urban planning

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

    following "Urban" or "urban"

    np_acts-logits-general · gemini-2.0-flash

    urban land, areas, cities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fermés
    -0.76
     createState
    -0.56
     supérieurs
    -0.54
     väli
    -0.53
    tvguidetime
    -0.53
     étrangères
    -0.52
     AssemblyProduct
    -0.52
     suivie
    -0.52
    ophores
    -0.49
    tl
    -0.49
    POSITIVE LOGITS
    isation
    0.75
     areas
    0.70
    WebVitals
    0.69
    izing
    0.68
    ized
    0.68
    iak
    0.64
    ised
    0.61
    ariato
    0.60
    ']],
    0.60
    ización
    0.60
    Activations Density 0.038%

    No Known Activations