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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 5061
    Prev
    Next
    INDEX
    Explanations

    phrases containing "Contact Us" and variations of contacting information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    guiente
    -0.62
     rootReducer
    -0.56
     myö
    -0.48
     fédé
    -0.48
    WebServlet
    -0.47
     mesmas
    -0.47
     esimer
    -0.47
    OVERR
    -0.45
     zijne
    -0.45
    pecabe
    -0.44
    POSITIVE LOGITS
     contact
    1.93
    contact
    1.88
    Contact
    1.79
     Contact
    1.76
     CONTACT
    1.65
    CONTACT
    1.62
     contacts
    1.59
    contacts
    1.48
     Contacts
    1.45
     kontakt
    1.41
    Activations Density 0.061%

    No Known Activations