© 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 - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 3507
    Prev
    Next
    INDEX
    Explanations

    mentions of various characters and their relationships in narratives

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     its
    -0.58
     itself
    -0.51
     оно
    -0.45
    它
    -0.43
    它的
    -0.41
     bylo
    -0.40
    itself
    -0.40
    Its
    -0.38
     Itself
    -0.38
    它是
    -0.37
    POSITIVE LOGITS
     who
    1.24
     whose
    0.95
     whom
    0.91
    AddTagHelper
    0.85
    whose
    0.82
     للمعارف
    0.81
     whofe
    0.80
     himself
    0.78
     quien
    0.76
    whom
    0.75
    Activations Density 0.709%

    No Known Activations