Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. MLP Out - 131k
    5. 6-GEMMASCOPE-MLP-131K
    6. 109764
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "of."

    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
    SequentialGroup
    -0.55
    INCREF
    -0.37
    instancetype
    -0.36
    tip
    -0.36
    Motiv
    -0.35
    ugno
    -0.35
    enumi
    -0.35
    inves
    -0.34
     Motiv
    -0.34
     dive
    -0.34
    POSITIVE LOGITS
     ویکی‌پدی
    0.67
     дописавши
    0.60
     للمعارف
    0.57
     Italijanski
    0.54
     يتيمه
    0.52
     désolés
    0.51
     ainfi
    0.50
    LEncoder
    0.50
    NameInMap
    0.50
     Theſe
    0.49
    Activations Density 0.006%

    No Known Activations