© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 14583
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "contact" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     femininos
    -0.64
     dezelve
    -0.63
     zijne
    -0.62
     diensten
    -0.60
     zelve
    -0.59
     mijne
    -0.59
     econômica
    -0.58
     disambiguazione
    -0.56
     aanzien
    -0.55
     umane
    -0.55
    POSITIVE LOGITS
     contacts
    1.14
     contact
    1.03
    contacts
    0.73
     Contacts
    0.70
     kontak
    0.68
    Contacts
    0.64
     contacted
    0.64
     contacting
    0.64
     contacto
    0.63
     Contact
    0.60
    Activations Density 0.455%

    No Known Activations