© 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. 3433
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names, particularly those starting with "Lou" or similar prefixes

    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
     ainfi
    -0.57
     mystère
    -0.57
     témoin
    -0.52
     régal
    -0.49
     verrez
    -0.49
     vœ
    -0.48
     témoignage
    -0.45
     bénéfice
    -0.44
    ChildScrollView
    -0.44
     mètre
    -0.43
    POSITIVE LOGITS
     Kou
    1.64
    Kou
    1.60
    rou
    1.59
    mou
    1.54
    oun
    1.49
    bou
    1.47
    OU
    1.47
    hou
    1.46
     Lou
    1.46
    ou
    1.46
    Activations Density 0.428%

    No Known Activations