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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 8302
    Prev
    Next
    INDEX
    Explanations

    occurrences of pixel specifications in CSS

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     verbunden
    -0.37
    ipeline
    -0.35
    illium
    -0.34
     покрытие
    -0.34
    forest
    -0.34
     estación
    -0.33
     kész
    -0.32
     Kalam
    -0.32
     ENJOY
    -0.32
     υπό
    -0.32
    POSITIVE LOGITS
    px
    3.72
     px
    2.52
    PX
    1.95
    Px
    1.83
     PX
    1.75
     Px
    1.55
     pixels
    1.10
     pixel
    1.01
     Pixels
    0.98
    pixels
    0.94
    Activations Density 0.043%

    No Known Activations