© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 17239
    Prev
    Next
    INDEX
    Explanations

    emotional expressions and relationships between characters

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    pronouns referring to people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Оно
    -0.80
     ModelExpression
    -0.68
     которое
    -0.67
    PerformLayout
    -0.66
    CppMethod
    -0.65
     betweenstory
    -0.65
     ujednoznacz
    -0.62
     wireType
    -0.61
     <=",
    -0.61
     CreateTagHelper
    -0.61
    POSITIVE LOGITS
     him
    0.79
    他是
    0.69
    她是
    0.64
     them
    0.63
     she
    0.63
     he
    0.58
     ellas
    0.52
     they
    0.52
     ihn
    0.48
    他们是
    0.47
    Activations Density 0.165%

    No Known Activations