© 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. 8621
    Prev
    Next
    INDEX
    Explanations

    references to the concept of focus or concentrating attention on particular topics or issues

    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
     ComVisible
    -1.05
    UnusedPrivate
    -0.93
     StatelessWidget
    -0.90
    ftagPool
    -0.81
    BeginContext
    -0.78
     StatefulWidget
    -0.75
    CloseOperation
    -0.72
    stateMutability
    -0.70
    AutoScaleMode
    -0.69
    !*\
    -0.68
    POSITIVE LOGITS
    nake
    0.53
     arbres
    0.50
     proportion
    0.48
    sweise
    0.44
    wad
    0.44
     drum
    0.43
     flesh
    0.42
     soste
    0.41
    schild
    0.41
     humanas
    0.40
    Activations Density 0.178%

    No Known Activations