© 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-2-9B
    7. MLP Out - 131k
    9. 6-GEMMASCOPE-MLP-131K
    11. 107948
    Prev
    Next
    INDEX
    Explanations

    references to native origins or native elements

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-mlp/layer_6/width_131k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.6.hook_mlp_out
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     native
    -1.38
    native
    -1.08
     nativo
    -0.98
     natives
    -0.96
     Native
    -0.95
    Native
    -0.90
     nativa
    -0.86
    NATIVE
    -0.75
     Natives
    -0.71
    natives
    -0.71
    POSITIVE LOGITS
    StoryboardSegue
    0.52
     useCallback
    0.44
    Pranala
    0.41
     raisonnable
    0.39
     pungkasnya
    0.38
    iformes
    0.37
     Verhältnis
    0.37
    enumi
    0.37
     condado
    0.37
     TAMBÉM
    0.36
    Activations Density 0.002%

    No Known Activations