© 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. 8003
    Prev
    Next
    INDEX
    Explanations

    phrases related to cancellations and actions taken out of respect

    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
     santo
    -0.50
     échou
    -0.48
     fehl
    -0.47
     Santo
    -0.46
    czes
    -0.46
    focal
    -0.45
    ız
    -0.45
     потер
    -0.44
     fluide
    -0.44
    Santo
    -0.44
    POSITIVE LOGITS
    CloseOperation
    1.01
     whim
    0.81
     curiosity
    0.79
    Personendaten
    0.71
     Vikipedi
    0.70
     voluntarily
    0.67
    WebVitals
    0.65
     purely
    0.64
    ">//
    0.63
     intentionally
    0.62
    Activations Density 0.428%

    No Known Activations