© 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. 9151
    Prev
    Next
    INDEX
    Explanations

    expressions of shame and humility

    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
     U
    -0.43
    mybatisplus
    -0.42
     pere
    -0.42
     Party
    -0.40
     interest
    -0.40
    لر
    -0.40
    ikut
    -0.39
     useSelector
    -0.39
     通販
    -0.38
    ali
    -0.37
    POSITIVE LOGITS
     shame
    1.12
    shame
    1.03
     فريبيس
    0.95
     Shame
    0.94
    Shame
    0.92
     honte
    0.89
    honor
    0.87
     disgrace
    0.85
     honor
    0.84
     ashamed
    0.84
    Activations Density 0.274%

    No Known Activations