© 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-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 12884
    Prev
    Next
    INDEX
    Explanations

    references to various types of "mu" or "mucilage."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Signalez
    -0.52
     للاسماء
    -0.46
    Tembelea
    -0.41
     Mumford
    -0.41
    ReusableCell
    -0.41
    ceğine
    -0.41
    AsUp
    -0.40
     jadx
    -0.39
     ویکی‌آمباردا
    -0.38
    Diwedd
    -0.38
    POSITIVE LOGITS
     Mu
    1.24
     mu
    1.21
    Mu
    1.13
     MU
    0.80
    Muz
    0.73
     AttributeSet
    0.63
    MU
    0.61
    docs
    0.61
     muco
    0.59
     muff
    0.56
    Activations Density 0.204%

    No Known Activations