© 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. 6355
    Prev
    Next
    INDEX
    Explanations

    user interface elements and notification types in a programming context

    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
    новништво
    -0.61
    StructEnd
    -0.51
    ](#
    -0.47
    ătoare
    -0.47
     समीक्षाओं
    -0.47
    +#+#
    -0.46
    мум
    -0.46
    ftagPool
    -0.46
    %</
    -0.46
    ChildScrollView
    -0.45
    POSITIVE LOGITS
     |
    1.84
    |
    1.76
     $|
    1.42
    .|
    1.29
    }|
    1.28
    |"
    1.25
    |\
    1.20
    )|
    1.19
     |
    1.19
    }|\
    1.18
    Activations Density 1.452%

    No Known Activations