© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 111236
    Prev
    Next
    INDEX
    Explanations

    terms related to directionality and directional detection in scientific contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     directional
    -1.98
     Directional
    -1.78
    directional
    -1.59
    Directional
    -1.57
     DIRECTION
    -1.09
    DIRECTION
    -1.03
     Direction
    -0.91
     direction
    -0.91
     directions
    -0.82
    direction
    -0.78
    POSITIVE LOGITS
    MethodManager
    0.49
    exitRule
    0.48
    TagMode
    0.48
     Roskov
    0.47
     själva
    0.45
    DeleteBehavior
    0.45
    expandindo
    0.44
    Tembelea
    0.43
    MLLoader
    0.42
     hijas
    0.42
    Activations Density 0.003%

    No Known Activations