© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. MLP Out - 16k
    9. 19-GEMMASCOPE-MLP-16K
    11. 10741
    Prev
    Next
    INDEX
    Explanations

    comparative phrases and exceptions in discussions of rules or generalizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_19/width_16k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_mlp_out
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     органов
    -0.39
    digkeit
    -0.37
    ielsen
    -0.37
     M
    -0.37
     G
    -0.37
     Bond
    -0.35
     To
    -0.34
     ber
    -0.34
    торы
    -0.34
    торов
    -0.34
    POSITIVE LOGITS
     exceptions
    2.42
     exception
    2.30
     Exceptions
    2.06
     excep
    1.84
    exception
    1.84
     Exception
    1.80
     EXCEPT
    1.77
     excepción
    1.75
    Exceptions
    1.73
    exceptions
    1.72
    Activations Density 0.433%

    No Known Activations