© 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. 24-GEMMASCOPE-RES-16K
    11. 7050
    Prev
    Next
    INDEX
    Explanations

    LaTeX symbols and formatting elements used in mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Mathematical or physics notation

    np_acts-logits-general · gemini-2.0-flash

    Ag^+^, nu

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Breen
    -0.90
     Reiss
    -0.83
     Loretta
    -0.81
     Ginn
    -0.80
     Hahn
    -0.77
     Agn
    -0.75
     ETI
    -0.75
     Turin
    -0.74
     Schaefer
    -0.74
     Tern
    -0.72
    POSITIVE LOGITS
     Samara
    0.63
     Hins
    0.61
     Vantage
    0.60
     Omar
    0.58
     Woodford
    0.58
     Garage
    0.55
    Ange
    0.55
    esar
    0.55
     Tomar
    0.55
     Yad
    0.55
    Activations Density 0.820%

    No Known Activations