© 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. 108956
    Prev
    Next
    INDEX
    Explanations

    phrases indicating reduced quantities or levels

    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
     lower
    -1.90
    lower
    -1.70
    Lower
    -1.66
     Lower
    -1.65
     LOWER
    -1.55
    LOWER
    -1.41
     unteren
    -1.11
     ниж
    -1.09
     lowers
    -1.05
     niž
    -0.97
    POSITIVE LOGITS
    Бахар
    0.54
    Xna
    0.49
     InputDecoration
    0.49
     TimeUnit
    0.49
    rawDesc
    0.47
    awtextra
    0.46
    edicated
    0.46
    heritance
    0.46
    ientí
    0.45
    MethodManager
    0.45
    Activations Density 0.016%

    No Known Activations