© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 111206
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "names"

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     names
    -1.73
     Names
    -1.62
    Names
    -1.43
    names
    -1.41
     NAMES
    -1.36
     nomes
    -1.16
    NAMES
    -1.14
     nombres
    -1.11
     Namen
    -1.01
     имена
    -0.85
    POSITIVE LOGITS
     ed
    0.33
    randn
    0.31
     Sol
    0.29
     le
    0.28
     Le
    0.27
     Fal
    0.27
     Bat
    0.26
     f
    0.26
    que
    0.26
     Cas
    0.26
    Activations Density 0.004%

    No Known Activations