© 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. 15813
    Prev
    Next
    INDEX
    Explanations

    repeated instances of the verb "is" and variations in sentence structure

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

    "Is" or "are" followed by an article

    np_acts-logits-general · gemini-2.0-flash

    is a/an/one

    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
     disambiguazione
    -0.85
     فريبيس
    -0.85
     betweenstory
    -0.78
     Houſe
    -0.77
    Diweddarwch
    -0.76
    GenerationType
    -0.75
     beginnetje
    -0.73
    AsUp
    -0.72
     nakalista
    -0.71
     becauſe
    -0.69
    POSITIVE LOGITS
     essentially
    0.86
     a
    0.80
     like
    0.77
     basically
    0.73
     certainly
    0.72
     both
    0.71
     such
    0.71
     an
    0.70
     neither
    0.67
     one
    0.66
    Activations Density 0.466%

    No Known Activations