© 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-2-2B
    7. MLP Out - 16k
    9. 19-GEMMASCOPE-MLP-16K
    11. 6322
    Prev
    Next
    INDEX
    Explanations

    questions starting with "why."

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_19/width_16k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_mlp_out
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     للمعارف
    -1.02
    DockStyle
    -0.95
    IsMutable
    -0.92
    ніципалі
    -0.91
    WebServlet
    -0.89
    MigrationBuilder
    -0.84
    SharedDtor
    -0.82
    ]")]
    -0.81
     ་་
    -0.81
    expandindo
    -0.80
    POSITIVE LOGITS
     بگ
    0.48
     we
    0.45
    aman
    0.45
     a
    0.44
     Ott
    0.43
     they
    0.43
     are
    0.42
     is
    0.42
       
    0.41
     he
    0.41
    Activations Density 0.136%

    No Known Activations