© 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. 108919
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize significance or importance in legal arguments

    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
     ویکی‌پدی
    -0.80
    +#+#
    -0.76
     noDo
    -0.71
     gynhyrchwyd
    -0.71
    তথ্যসূত্র
    -0.67
    ⓧ
    -0.65
    +#+
    -0.65
    ագրություններ
    -0.60
     وتسجيلات
    -0.60
     الرياضيه
    -0.59
    POSITIVE LOGITS
     vroe
    0.37
     stanow
    0.35
    chränk
    0.35
    avaient
    0.35
     Burrows
    0.34
     verkligen
    0.34
    แป
    0.34
    ConstraintSet
    0.32
    ไว้
    0.32
     forskjellige
    0.32
    Activations Density 0.002%

    No Known Activations