© 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-2-9B
    7. MLP Out - 131k
    9. 6-GEMMASCOPE-MLP-131K
    11. 109435
    Prev
    Next
    INDEX
    Explanations

    variations of the word "say" in different forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-mlp/layer_6/width_131k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.6.hook_mlp_out
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ays
    -2.36
    AYS
    -1.67
    AY
    -0.79
    ay
    -0.79
     Kays
    -0.75
     Mays
    -0.73
    lays
    -0.73
     Bays
    -0.72
     days
    -0.68
    days
    -0.64
    POSITIVE LOGITS
     termica
    0.53
     vectorielle
    0.53
    pexpr
    0.50
     wikipagina
    0.45
     zijne
    0.44
    AddTagHelper
    0.44
    Identyfik
    0.44
     podjet
    0.42
     $_"
    0.42
     Manfaat
    0.42
    Activations Density 0.001%

    No Known Activations