© 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. 108934
    Prev
    Next
    INDEX
    Explanations

    tags and formatting related to HTML or web content

    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
     فريبيس
    -0.66
    Personendaten
    -0.62
    Aholisi
    -0.61
     مشين
    -0.61
     propOrder
    -0.58
    +#+#
    -0.57
     AssemblyCulture
    -0.57
    ChildIndex
    -0.54
    parsedMessage
    -0.53
    EDEFAULT
    -0.52
    POSITIVE LOGITS
    rzez
    0.49
     bırak
    0.40
     conosco
    0.38
     sisält
    0.37
    ปร
    0.35
     سف
    0.35
     creș
    0.35
    culada
    0.34
    labels
    0.34
     환
    0.34
    Activations Density 0.006%

    No Known Activations