© 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. MLP Out - 16k
    9. 19-GEMMASCOPE-MLP-16K
    11. 9073
    Prev
    Next
    INDEX
    Explanations

    negative or warning indicators typically associated with errors or issues

    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
     myſelf
    -1.00
    StructEnd
    -0.96
     transfieras
    -0.94
     ExecuteAsync
    -0.92
     ویکی‌پدیای
    -0.89
     Efq
    -0.88
     Jefus
    -0.88
    Бахар
    -0.87
     Theſe
    -0.86
     estekak
    -0.85
    POSITIVE LOGITS
    Entry
    0.44
     vs
    0.41
     entry
    0.41
     super
    0.41
     versus
    0.39
     مقاب
    0.39
     kohta
    0.39
      
    0.39
     itong
    0.39
     i
    0.38
    Activations Density 0.416%

    No Known Activations