© 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. 11-GEMMASCOPE-RES-16K
    11. 8704
    Prev
    Next
    INDEX
    Explanations

    statements or assertions presented as facts

    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
     DP
    -0.36
     Comb
    -0.36
    EndContext
    -0.36
    pography
    -0.35
    postmedia
    -0.35
    жности
    -0.34
    forKey
    -0.34
    难
    -0.34
    SourceChecksum
    -0.33
     vignette
    -0.33
    POSITIVE LOGITS
     fact
    0.85
     anzi
    0.80
     indeed
    0.80
     infatti
    0.77
    indeed
    0.77
     bahkan
    0.76
    Indeed
    0.76
    事实上
    0.75
    Bahkan
    0.74
     Bahkan
    0.73
    Activations Density 0.192%

    No Known Activations