© 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. 2-GEMMASCOPE-RES-16K
    11. 16049
    Prev
    Next
    INDEX
    Explanations

    mentions of specific individuals referred to as "Mr" or "Ms."

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ToBounds
    -0.40
    cahontas
    -0.40
    ofas
    -0.37
    だったが
    -0.37
     שוליים
    -0.37
    minecraftforge
    -0.37
    HasAnnotation
    -0.36
    vetica
    -0.36
    だよね
    -0.35
     링크
    -0.35
    POSITIVE LOGITS
     Mr
    3.47
    Mr
    3.19
     mr
    2.66
    mr
    2.20
     Mrs
    2.14
     Ms
    2.06
     MR
    1.98
    Mrs
    1.96
     Mister
    1.95
     Messrs
    1.93
    Activations Density 0.099%

    No Known Activations