© 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. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105347
    Prev
    Next
    INDEX
    Explanations

    expressions of emotional conflict and longing

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Winaray
    -0.61
     للاسماء
    -0.53
    DotNetBar
    -0.47
    想必
    -0.45
    只有一
    -0.45
    énu
    -0.45
     Aussicht
    -0.44
    \{\\
    -0.44
     logr
    -0.43
    Carriera
    -0.43
    POSITIVE LOGITS
    rawDesc
    0.47
     ProtoMessage
    0.44
    StructEnd
    0.38
     feelings
    0.34
     sentimientos
    0.34
    InjectAttribute
    0.34
     Gefühle
    0.33
     الحره
    0.33
     dormitórios
    0.33
    >{@
    0.32
    Activations Density 0.020%

    No Known Activations