© 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. 31-GEMMASCOPE-RES-16K
    11. 3247
    Prev
    Next
    INDEX
    Explanations

    references to names or titles of places, entities, or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word "named" and surrounding context indicating that something is named after a person or place.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Билгалдахарш
    -0.70
    цездатний
    -0.64
    expandindo
    -0.63
     <<<<<<<<<<<<<<
    -0.63
    httphttps
    -0.62
     المعيارى
    -0.61
    transQ
    -0.59
     autorytatywna
    -0.59
     initComponents
    -0.57
    évaluateur
    -0.57
    POSITIVE LOGITS
     named
    1.45
    named
    1.38
    Named
    1.36
     Named
    1.32
     namesake
    1.12
     naming
    1.06
    命名
    1.00
     homenagem
    0.90
     genoemd
    0.87
    naming
    0.85
    Activations Density 0.314%

    No Known Activations