© 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 EvalsExportsinterp-engineNEWAPI 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. 7103
    Prev
    Next
    INDEX
    Explanations

    references to performance and stunts associated with a show or production

    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
     operating
    -0.54
    MLLoader
    -0.53
    Operating
    -0.52
    jfree
    -0.51
     Signalez
    -0.50
     operate
    -0.48
    makeText
    -0.46
    ScopeManager
    -0.46
     Operating
    -0.46
     Vertra
    -0.45
    POSITIVE LOGITS
     Sequences
    0.69
     виправивши
    0.66
     action
    0.66
     sequences
    0.66
     sequence
    0.63
    indakan
    0.61
    アクション
    0.60
     ACTION
    0.60
     Sequence
    0.60
     Action
    0.59
    Activations Density 0.250%

    No Known Activations