© 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. 18-GEMMASCOPE-RES-16K
    11. 9144
    Prev
    Next
    INDEX
    Explanations

    words containing the sound "aw" or "ow" related to names or proper nouns

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

    with repeated "w" sounds

    np_acts-logits-general · gemini-2.0-flash

    words starting with aw, jaw, baw, cow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -0.76
     насељу
    -0.66
     Clancy
    -0.64
    coroutines
    -0.63
    erende
    -0.62
    IDATE
    -0.61
    alisa
    -0.61
    yari
    -0.61
    ???:
    -0.60
     الحره
    -0.59
    POSITIVE LOGITS
    ww
    1.08
    wwww
    1.07
    wwwwwwww
    1.04
    wwwww
    0.96
     Kow
    0.95
     Prow
    0.95
    WWWW
    0.94
     Baw
    0.93
    daw
    0.92
     Waw
    0.89
    Activations Density 0.311%

    No Known Activations