© 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. 6386
    Prev
    Next
    INDEX
    Explanations

    kernel and file system paths within a Unix-like operating system

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    "]}
    -0.47
    Související
    -0.46
    ofire
    -0.45
     underv
    -0.44
    plom
    -0.43
     fell
    -0.42
    invokeLater
    -0.41
     honors
    -0.40
    щихся
    -0.39
     touched
    -0.39
    POSITIVE LOGITS
    tvguidetime
    0.91
    sizeCache
    0.77
    ModelAdmin
    0.70
    jalá
    0.66
    matchCondition
    0.66
    webElementXpaths
    0.65
     TextInputType
    0.65
     Exacts
    0.64
    Xna
    0.59
    Билгалдахарш
    0.59
    Activations Density 0.227%

    No Known Activations