© 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. 1-GEMMASCOPE-RES-16K
    11. 9715
    Prev
    Next
    INDEX
    Explanations

    expressions of perfection or ideal quality

    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
    اعمال
    -0.44
    merksamkeit
    -0.41
    舐
    -0.40
    cope
    -0.39
    how
    -0.38
    jaan
    -0.38
     Kary
    -0.38
    aites
    -0.38
     nuevamente
    -0.38
     ویکی‌پدی
    -0.38
    POSITIVE LOGITS
     perfect
    0.87
    perfect
    0.87
    Perfect
    0.84
     Perfect
    0.84
     perfectos
    0.79
     PERFECT
    0.76
    PERFECT
    0.73
     perfecte
    0.64
    完美
    0.64
     perfeito
    0.63
    Activations Density 0.195%

    No Known Activations