© 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. 111157
    Prev
    Next
    INDEX
    Explanations

    instances of the word "follow" and its variations, indicating a focus on actions related to following or observing

    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
     незавершена
    -0.59
    adaptiveStyles
    -0.43
     istrinya
    -0.42
    
    -0.42
     leveren
    -0.41
    şört
    -0.41
     hiperten
    -0.40
     trekken
    -0.39
    akaian
    -0.39
    Espèce
    -0.38
    POSITIVE LOGITS
    tanleria
    0.52
     unknownFields
    0.49
    Bibliografía
    0.48
    Viitteet
    0.44
    Bakgrunnsstoff
    0.43
     utafitiHapana
    0.42
     ***!
    0.41
    moine
    0.39
    тература
    0.39
    shutil
    0.39
    Activations Density 0.004%

    No Known Activations