© 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. 20-GEMMASCOPE-RES-16K
    11. 972
    Prev
    Next
    INDEX
    Explanations

    references to numbers and quantities, particularly in a social or legal context

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

    Cardinal numbers followed by "people" or similar terms

    np_acts-logits-general · gemini-2.0-flash

    number of persons

    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
    Parental
    -0.51
    Erreferentziak
    -0.50
     démocr
    -0.49
    ніципа
    -0.47
    aternal
    -0.47
     vœux
    -0.47
     AssemblyCulture
    -0.46
    CHEZ
    -0.45
     vectorielles
    -0.45
    InsertCommand
    -0.44
    POSITIVE LOGITS
     persons
    1.89
     person
    1.84
     people
    1.76
     individuals
    1.75
     personnes
    1.44
    individuals
    1.43
    persons
    1.40
     personen
    1.38
     personer
    1.35
    people
    1.33
    Activations Density 0.909%

    No Known Activations