© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 16331
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "way" in different contexts

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

    The token "way" followed by an adverb or preposition

    np_acts-logits-general · gemini-2.0-flash

    way and subsequent words

    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
     ExecuteAsync
    -0.87
    XMLSchema
    -0.87
    expandindo
    -0.82
    GEBURTSDATUM
    -0.79
     ActiveRecord
    -0.77
    PerformLayout
    -0.76
     transférez
    -0.74
    ReusableCell
    -0.74
     loisirs
    -0.73
     nakalista
    -0.72
    POSITIVE LOGITS
    farers
    0.92
    farer
    0.89
     WAY
    0.85
     Way
    0.79
    faring
    0.78
     ways
    0.74
     way
    0.74
    yyy
    0.72
    Ways
    0.72
     Ways
    0.71
    Activations Density 0.088%

    No Known Activations