© 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. 111410
    Prev
    Next
    INDEX
    Explanations

    instances of the character "ú" in various contexts

    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
    ú
    -2.13
    uacute
    -1.68
    Ú
    -1.51
     Ú
    -1.02
     ú
    -0.93
    Personendaten
    -0.84
    út
    -0.76
    ún
    -0.75
     CreateTagHelper
    -0.73
    ù
    -0.73
    POSITIVE LOGITS
    elemField
    0.50
     szóci
    0.38
    Vidite
    0.35
    Jîn
    0.35
    tling
    0.35
    forder
    0.35
    graphie
    0.35
    när
    0.34
    gebäude
    0.34
     boty
    0.34
    Activations Density 0.001%

    No Known Activations