© 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. 5-GEMMASCOPE-RES-16K
    11. 13542
    Prev
    Next
    INDEX
    Explanations

    instances or phrases indicating automated processes or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nier
    -0.79
    lihood
    -0.78
    Personensuche
    -0.76
     AssemblyProduct
    -0.73
     TextFormField
    -0.70
    hound
    -0.68
     TZ
    -0.67
    endsection
    -0.67
    DllImport
    -0.65
    PMailer
    -0.64
    POSITIVE LOGITS
     automatic
    2.06
     Automatic
    2.00
     automatically
    1.94
    Automatic
    1.92
    automatic
    1.91
     AUTOMATIC
    1.82
    automatically
    1.66
     Automatically
    1.64
     automat
    1.64
    Automatically
    1.59
    Activations Density 0.099%

    No Known Activations