© 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-2-2B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 9698
    Prev
    Next
    INDEX
    Explanations

    instances of the word "coming."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.74
    PDOException
    -0.74
     Majefty
    -0.71
    bitField
    -0.71
     AssemblyProduct
    -0.70
     purpoſe
    -0.69
    DeleteCommand
    -0.68
    encodeWith
    -0.66
     архивлан
    -0.65
    oneofs
    -0.65
    POSITIVE LOGITS
     come
    3.36
     coming
    3.30
     comes
    3.11
     came
    2.92
     Coming
    2.92
     Come
    2.91
    Coming
    2.85
    Come
    2.81
     COME
    2.81
     Comes
    2.77
    Activations Density 0.067%

    No Known Activations