© 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. 18-GEMMASCOPE-RES-16K
    11. 10755
    Prev
    Next
    INDEX
    Explanations

    references to specific locations and communities

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

    Follows "of", commas, or "in"

    np_acts-logits-general · gemini-2.0-flash

    UK places and regions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.80
     AssemblyCulture
    -0.73
     ExecuteAsync
    -0.72
    noinspection
    -0.71
    WithIOException
    -0.65
    Württemberg
    -0.64
     lobster
    -0.64
    >{@
    -0.63
     Habib
    -0.62
    NewUrlParser
    -0.61
    POSITIVE LOGITS
     Hertfordshire
    0.82
     Haryana
    0.80
     Hatfield
    0.60
     Denton
    0.57
     Edmonton
    0.57
     Tottenham
    0.53
     neuro
    0.51
     Hert
    0.50
    Oise
    0.49
    匈
    0.49
    Activations Density 0.193%

    No Known Activations