© 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. 12326
    Prev
    Next
    INDEX
    Explanations

    statements made by individuals regarding their experiences or responses

    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
     CURIAM
    -0.58
    нительно
    -0.54
    ecore
    -0.51
    曖昧さ回避
    -0.50
    Ễ
    -0.48
    Ƚ
    -0.47
    XmlAccessorType
    -0.46
     geográfica
    -0.46
    lardır
    -0.44
    webkit
    -0.44
    POSITIVE LOGITS
     statement
    1.94
     Statement
    1.63
    statement
    1.63
     statements
    1.56
    Statement
    1.53
     STATEMENT
    1.50
     Statements
    1.47
    STATEMENT
    1.36
    statements
    1.32
    Statements
    1.30
    Activations Density 0.290%

    No Known Activations