© 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. 0-GEMMASCOPE-RES-16K
    11. 2723
    Prev
    Next
    INDEX
    Explanations

    references to committees and their activities

    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
     autorytatywna
    -0.71
    AnchorStyles
    -0.57
    :+:
    -0.51
     pauv
    -0.50
     AssemblyCompany
    -0.50
    Tazama
    -0.50
    makeText
    -0.49
    ंदीखरीदारी
    -0.49
     reformed
    -0.48
    GIVEREF
    -0.48
    POSITIVE LOGITS
    Razor
    0.49
    EST
    0.47
    est
    0.45
    committee
    0.40
     committee
    0.40
    Expected
    0.36
     полага
    0.36
     Partagez
    0.36
    GHIJKLM
    0.35
     CHtml
    0.34
    Activations Density 0.370%

    No Known Activations