© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 110907
    Prev
    Next
    INDEX
    Explanations

    terms related to technology, especially involving smart devices and intelligent systems

    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
     Smart
    -0.58
    Intelligent
    -0.56
     smart
    -0.55
     intelligent
    -0.54
     Intelligent
    -0.54
     هوشمند
    -0.54
     smartly
    -0.52
    smart
    -0.49
    Smart
    -0.49
     inteligente
    -0.48
    POSITIVE LOGITS
     ơi
    0.42
    ⓧ
    0.41
     myſelf
    0.39
    ByPrimaryKey
    0.38
    WithMany
    0.35
     lenguaje
    0.33
     Offisielt
    0.32
     comigo
    0.32
     Majefty
    0.32
     autorytatywna
    0.32
    Activations Density 0.008%

    No Known Activations