© 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. 4-GEMMASCOPE-RES-16K
    11. 11499
    Prev
    Next
    INDEX
    Explanations

    symbols and formatting commonly used in markup languages or programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Spoljašnje
    -0.73
    ThroughAttribute
    -0.71
     Somers
    -0.70
    piac
    -0.69
     Altern
    -0.68
     Idd
    -0.68
     InputDecoration
    -0.66
     Siga
    -0.65
    EndContext
    -0.63
     Maynard
    -0.63
    POSITIVE LOGITS
     là
    1.65
    là
    1.18
     Là
    1.15
    Là
    1.05
    人是
    0.76
    是
    0.75
    ilà
    0.75
     adalah
    0.72
    adalah
    0.72
     của
    0.72
    Activations Density 0.016%

    No Known Activations