© 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. 107998
    Prev
    Next
    INDEX
    Explanations

    the suffix "ute" and its variations in different 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
    ute
    -2.31
    utes
    -2.03
    UTE
    -2.00
    UTES
    -1.59
    uted
    -1.11
    uten
    -1.09
    uting
    -1.06
     ute
    -1.02
    utek
    -0.93
    utet
    -0.93
    POSITIVE LOGITS
    ंदीखरीदारी
    0.46
    awtextra
    0.44
     reset
    0.41
     CommonModule
    0.40
    adaptiveStyles
    0.40
    Concurrency
    0.40
    Feast
    0.39
    RetentionPolicy
    0.37
     HFILL
    0.37
     BaseModel
    0.36
    Activations Density 0.004%

    No Known Activations