© 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-2-9B
    7. MLP Out - 131k
    9. 6-GEMMASCOPE-MLP-131K
    11. 109388
    Prev
    Next
    INDEX
    Explanations

    specific components related to tanks and boilers in various contexts

    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
    WriteTagHelper
    -0.87
    TagMode
    -0.79
    elemField
    -0.78
    ⓧ
    -0.74
    UserScript
    -0.73
    PyExc
    -0.72
     '\\;'
    -0.72
    Autoritní
    -0.70
     autorytatywna
    -0.69
    AddTagHelper
    -0.68
    POSITIVE LOGITS
     multi
    0.28
     प्रति
    0.28
    Multi
    0.27
    Synonymes
    0.27
     single
    0.25
    料
    0.25
     Multi
    0.25
    ை
    0.25
    Instantiate
    0.25
     Jung
    0.24
    Activations Density 0.001%

    No Known Activations