© 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. 109079
    Prev
    Next
    INDEX
    Explanations

    references to offline capabilities or settings

    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
     offline
    -1.66
     Offline
    -1.44
    offline
    -1.38
    Offline
    -1.27
    线下
    -0.69
     IRL
    -0.66
    オフ
    -0.58
     irl
    -0.58
     unplugged
    -0.51
     Samaria
    -0.49
    POSITIVE LOGITS
     initComponents
    0.62
    TypedDataSet
    0.45
    Tembelea
    0.41
    Чыганаклар
    0.41
    findpost
    0.41
     utafitiHapana
    0.40
    Pratique
    0.40
    XmlAccessorType
    0.39
    Hochspringen
    0.38
    rawDesc
    0.38
    Activations Density 0.002%

    No Known Activations