© 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-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 6354
    Prev
    Next
    INDEX
    Explanations

    personal expressions of excitement or happiness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     even
    -0.91
     sogar
    -0.83
     dessutom
    -0.80
     incluso
    -0.79
     même
    -0.78
     moreover
    -0.75
    even
    -0.75
     malah
    -0.74
     also
    -0.73
     zudem
    -0.73
    POSITIVE LOGITS
     awalnya
    0.58
     originally
    0.56
    ंदीखरीदारी
    0.56
     initially
    0.55
     ordinarily
    0.54
     inicialmente
    0.54
    一開始
    0.53
     traditionally
    0.53
     originalmente
    0.53
     zunächst
    0.52
    Activations Density 0.955%

    No Known Activations