© 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. 1-GEMMASCOPE-RES-16K
    11. 9233
    Prev
    Next
    INDEX
    Explanations

    repeated and nested instances of the term "mu" followed by indices or modifications, suggesting a focus on mathematical notation or concepts related to mu in a scientific or technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.50
     Mund
    -0.47
     Bisnis
    -0.47
    Mund
    -0.46
    mund
    -0.46
    UnsafeEnabled
    -0.44
     otot
    -0.42
     Muscular
    -0.42
     Komunikasi
    -0.42
     settling
    -0.41
    POSITIVE LOGITS
     Mu
    1.81
    Mu
    1.64
     mu
    1.53
    mu
    1.45
     MU
    1.20
    MU
    1.07
    Muz
    0.85
    Muff
    0.76
     muzzle
    0.68
     ProtoMessage
    0.65
    Activations Density 0.298%

    No Known Activations