© 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. 12239
    Prev
    Next
    INDEX
    Explanations

    syntactic structures related to method or function definitions in programming

    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
    MessageTagHelper
    -1.02
    Personensuche
    -0.99
     الحره
    -0.98
    ActionCreators
    -0.91
     nahilalakip
    -0.87
     سكانية
    -0.84
     Chwiliwch
    -0.83
     ddelweddau
    -0.82
     SwitchCompat
    -0.81
     Exactos
    -0.80
    POSITIVE LOGITS
     uns
    0.46
    ://
    0.46
     un
    0.43
    وار
    0.43
     Rot
    0.41
     Ret
    0.41
     Un
    0.41
     wore
    0.41
     raw
    0.41
     pat
    0.40
    Activations Density 0.175%

    No Known Activations