© 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. 22-GEMMASCOPE-RES-16K
    11. 13418
    Prev
    Next
    INDEX
    Explanations

    inflections of the verb "will"

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

    Contractions with "'ll" followed by a verb or adverb

    np_acts-logits-general · gemini-2.0-flash

    'll followed by a verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ArgumentParser
    -0.66
     BoxDecoration
    -0.63
    styleable
    -0.60
    RegistryLite
    -0.60
    DoubleQuotes
    -0.60
    inburgh
    -0.59
     المعيارى
    -0.59
     שוליים
    -0.58
    EDEFAULT
    -0.57
    accéder
    -0.57
    POSITIVE LOGITS
     gladly
    0.59
     adelante
    0.58
     be
    0.58
    modelBuilder
    0.56
     admit
    0.56
     wait
    0.53
    RunAsync
    0.51
    happily
    0.49
     try
    0.49
     bientôt
    0.48
    Activations Density 0.096%

    No Known Activations