© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. MLP Out - 131k
    5. 6-GEMMASCOPE-MLP-131K
    6. 108802
    Prev
    Next
    INDEX
    Explanations

    instances of the term "cohomology" and its variations in different 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
     co
    -0.80
     Co
    -0.64
    Co
    -0.44
     cof
    -0.41
    co
    -0.41
     współ
    -0.38
     cop
    -0.36
    共
    -0.36
     coc
    -0.35
     Cot
    -0.33
    POSITIVE LOGITS
    ьаж
    0.77
    évaluateur
    0.75
    RenderAtEndOf
    0.73
     समीक्षाओं
    0.71
    SourceChecksum
    0.70
    تقاوى
    0.66
     Савезне
    0.65
    rungsseite
    0.64
    tagHelperRunner
    0.64
     للمعارف
    0.63
    Activations Density 0.026%

    No Known Activations