© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 15762
    Prev
    Next
    INDEX
    Explanations

    references to centers or facilities, particularly those associated with specialized functions or services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Babi
    -0.46
     Gio
    -0.45
    IOException
    -0.44
     Pil
    -0.43
     Salom
    -0.43
     Wie
    -0.43
     Phy
    -0.42
     Jak
    -0.42
     Geol
    -0.42
     swore
    -0.42
    POSITIVE LOGITS
     Center
    2.59
     center
    2.52
    Center
    2.50
     Centre
    2.36
     CENTER
    2.30
     centre
    2.30
    Centre
    2.30
    center
    2.23
     centers
    2.19
     Centers
    2.09
    Activations Density 0.060%

    No Known Activations