© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 109439
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and their molecular formulas

    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
    ↵
    -0.33
     hyp
    -0.33
    en
    -0.31
    sing
    -0.31
    пы
    -0.31
     הי
    -0.30
     reaction
    -0.30
     sadar
    -0.30
    GroupLayout
    -0.30
    四人
    -0.30
    POSITIVE LOGITS
     kasarigan
    0.78
     myſelf
    0.74
    تقاوى
    0.65
     Reſ
    0.64
     Anſ
    0.64
    цездатний
    0.64
     houſe
    0.63
    addCriterion
    0.63
     ſta
    0.62
     Houſe
    0.61
    Activations Density 0.543%

    No Known Activations