© 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. 9281
    Prev
    Next
    INDEX
    Explanations

    references to organizational decision-making and collaboration in project management

    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
    delwed
    -0.74
     propOrder
    -0.62
    ADVERTISEMENT
    -0.58
    ::_('
    -0.54
    hyrchwyd
    -0.52
    esModule
    -0.52
    ainville
    -0.52
     HasFactory
    -0.51
    scry
    -0.50
    haru
    -0.49
    POSITIVE LOGITS
     undertake
    0.92
     undertook
    0.88
     undertaken
    0.86
     undertakes
    0.85
     attempted
    0.82
     tackled
    0.82
     undertaking
    0.81
     emprender
    0.76
     accett
    0.75
     relever
    0.75
    Activations Density 0.307%

    No Known Activations