© 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-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 16053
    Prev
    Next
    INDEX
    Explanations

    references to bubbles or processes involving bubbles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 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
    ⓧ
    -0.96
    ViewImports
    -0.86
    NOPQRST
    -0.83
    /**
    -0.81
    iastes
    -0.81
    IANGLES
    -0.80
    ]>
    -0.80
    ктан
    -0.79
    Personensuche
    -0.77
    kegaard
    -0.77
    POSITIVE LOGITS
     bubble
    1.90
     Bubble
    1.83
    bubble
    1.69
    Bubble
    1.64
     bubbles
    1.61
    bubbles
    1.45
     Bubbles
    1.42
     burbuja
    1.29
     BUB
    1.20
     bubbling
    1.11
    Activations Density 0.048%

    No Known Activations