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

    Neuronpedia

    Jacobian LensNEW
    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. 2-GEMMASCOPE-RES-16K
    11. 182
    Prev
    Next
    INDEX
    Explanations

    a high frequency of the word "um" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 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
    ="{
    -0.56
    lucene
    -0.52
    <strong>
    -0.52
    بوابة
    -0.49
    酚
    -0.48
     consumption
    -0.47
    Source
    -0.46
    शा
    -0.46
    GeneratedCode
    -0.46
    老
    -0.46
    POSITIVE LOGITS
     um
    2.69
     Um
    2.29
    Um
    2.02
     uh
    1.66
     umm
    1.48
     ums
    1.43
     Uh
    1.41
     UM
    1.39
     Umm
    1.24
     Uma
    1.20
    Activations Density 0.025%

    No Known Activations