© 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. 9191
    Prev
    Next
    INDEX
    Explanations

    phrases related to overwhelming experiences or emotions

    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
     jsonify
    -0.45
    rrggbb
    -0.43
    tagext
    -0.42
    JMenu
    -0.42
     Zusch
    -0.38
    aarrggbb
    -0.38
    ActionCreators
    -0.37
    Œuvres
    -0.36
     annually
    -0.36
     virtù
    -0.36
    POSITIVE LOGITS
     overwhelmed
    0.72
     overwhelming
    0.67
     ویکی‌پدی
    0.61
     overwhel
    0.59
     overwhelm
    0.56
     crunch
    0.54
     pole
    0.53
     whips
    0.53
     breakdown
    0.53
    Breakdown
    0.53
    Activations Density 0.455%

    No Known Activations