© 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-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 5085
    Prev
    Next
    INDEX
    Explanations

    start of sections or paragraphs in texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 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
    JComboBox
    -0.80
     Shand
    -0.78
    Vidite
    -0.76
    estacks
    -0.73
     Betracht
    -0.73
    antMatchers
    -0.71
    çalves
    -0.70
    }{*}{
    -0.70
    folger
    -0.70
     MenuView
    -0.70
    POSITIVE LOGITS
    
    1.35
    <bos>
    0.60
     Monfieur
    0.59
    labili
    0.57
     immemorial
    0.54
     doubtnut
    0.53
     poffible
    0.53
     Antrim
    0.52
     uſed
    0.52
    
    0.52
    Activations Density 0.031%

    No Known Activations