© 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. 21-GEMMASCOPE-RES-16K
    11. 2396
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "moo" or sounds resembling it in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الحره
    -0.67
     Meksiku
    -0.64
    Rhestr
    -0.63
    ️
    -0.63
    uxxxx
    -0.62
    sschutz
    -0.60
     ویکی‌آمباردا
    -0.60
    ghua
    -0.60
    principalColumn
    -0.58
    ψε
    -0.58
    POSITIVE LOGITS
     hoo
    0.72
     hee
    0.68
     Noo
    0.65
    hoo
    0.65
    Boo
    0.63
    OOT
    0.62
     BOO
    0.61
     Moos
    0.61
    Doo
    0.60
    Hoo
    0.60
    Activations Density 0.206%

    No Known Activations