© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10026
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to wiring and circuitry

    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
    φων
    -0.42
     hogy
    -0.40
     نظر
    -0.39
    #__
    -0.39
     bas
    -0.38
     dra
    -0.38
    ため
    -0.37
    상
    -0.37
    cas
    -0.37
    das
    -0.36
    POSITIVE LOGITS
     ultimately
    1.23
     eventually
    1.14
    eventually
    1.13
     subsequently
    1.08
     originally
    1.06
     initially
    1.03
     ordinarily
    1.02
     previously
    1.01
     now
    1.00
     fometimes
    0.99
    Activations Density 0.997%

    No Known Activations