© 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-2-9B
    7. MLP Out - 131k
    9. 6-GEMMASCOPE-MLP-131K
    11. 108476
    Prev
    Next
    INDEX
    Explanations

    important phrases related to instructions and procedures

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     hled
    -0.27
     financiación
    -0.25
     incorporación
    -0.25
    
    -0.24
     realización
    -0.23
     Administración
    -0.22
     señalado
    -0.22
     solicitó
    -0.22
    īdz
    -0.22
     scă
    -0.22
    POSITIVE LOGITS
    ########.
    0.95
    AccessorTable
    0.91
     surla
    0.77
     CreateTagHelper
    0.77
    AddTagHelper
    0.76
    MemoryWarning
    0.76
     Houſe
    0.73
    ViewFeatures
    0.73
     Chriftian
    0.72
    matchCondition
    0.71
    Activations Density 0.051%

    No Known Activations