© 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. 9-GEMMASCOPE-RES-16K
    11. 7124
    Prev
    Next
    INDEX
    Explanations

    symbols and punctuation used in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    बा
    -0.81
    ing
    -0.79
    WriteLiteral
    -0.79
    ่
    -0.78
    makeConstraints
    -0.77
    razor
    -0.74
     
    -0.73
    ат
    -0.72
     Teb
    -0.72
    ি
    -0.68
    POSITIVE LOGITS
     myſelf
    1.11
     iſt
    1.09
    ."</
    1.07
     Jefus
    1.07
     Chriſt
    0.94
     ſy
    0.93
     Monfieur
    0.93
     pleaſure
    0.92
     $_"
    0.92
    ſelves
    0.92
    Activations Density 0.247%

    No Known Activations