© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 5799
    Prev
    Next
    INDEX
    Explanations

    comparative phrases indicating a reduction or decrease

    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
    bingen
    -0.83
     Kirkwood
    -0.72
     AssemblyTitle
    -0.71
    ratulations
    -0.71
     BoxDecoration
    -0.70
    skosten
    -0.69
    روزی
    -0.69
    urfs
    -0.67
    WebMethod
    -0.66
    marry
    -0.66
    POSITIVE LOGITS
     less
    1.90
     Less
    1.80
     LESS
    1.74
    Less
    1.72
    less
    1.46
     moins
    1.34
    LESS
    1.33
     menos
    1.30
     weniger
    1.24
     fewer
    1.22
    Activations Density 0.088%

    No Known Activations