© 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. 16045
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "contact"

    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
     namorados
    -0.37
    eneration
    -0.35
     Cow
    -0.35
     avoient
    -0.35
     CardView
    -0.34
     Sher
    -0.33
     derived
    -0.33
     Piala
    -0.32
     ferramenta
    -0.32
     Industry
    -0.31
    POSITIVE LOGITS
    Contact
    2.19
     Contact
    2.16
    contact
    2.00
     CONTACT
    1.98
     contact
    1.88
    CONTACT
    1.88
     Contacts
    1.75
     contacts
    1.73
    contacts
    1.68
     contacted
    1.66
    Activations Density 0.084%

    No Known Activations