© 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. 9073
    Prev
    Next
    INDEX
    Explanations

    references to quantities and counts, particularly using terms related to one or more items

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

    "une" or "un" followed by another word

    np_acts-logits-general · gemini-2.0-flash

    quantifiers and indefinite articles

    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
     myſelf
    -0.83
     OFDb
    -0.82
     Jefus
    -0.80
     himſelf
    -0.80
     itſelf
    -0.80
     Majefty
    -0.79
     greateſt
    -0.78
     ſche
    -0.77
     raiſ
    -0.76
     becauſe
    -0.75
    POSITIVE LOGITS
     certain
    0.83
     very
    0.80
     cuantos
    0.74
     considerable
    0.73
     large
    0.72
     kind
    0.71
     few
    0.70
     good
    0.69
     fairly
    0.67
     rather
    0.67
    Activations Density 0.016%

    No Known Activations