© 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. 108267
    Prev
    Next
    INDEX
    Explanations

    specific identifiers or names related to various subjects or entities in text

    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
    MigrationBuilder
    -0.63
    VersionUID
    -0.61
    Przypisy
    -0.59
    CloseOperation
    -0.57
    othek
    -0.56
    PARATOR
    -0.56
    alej
    -0.54
     inconven
    -0.52
    
    -0.52
     okuyayım
    -0.51
    POSITIVE LOGITS
     vPvB
    0.33
     onely
    0.31
     revolución
    0.29
    tagPool
    0.29
     jongen
    0.27
    cuerdo
    0.27
    impianto
    0.27
     případ
    0.27
     supervivencia
    0.26
     aDecoder
    0.26
    Activations Density 0.515%

    No Known Activations