© 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. 15-GEMMASCOPE-RES-16K
    11. 12427
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and structures related to set theory and function spaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Scénario
    -0.74
     Gallen
    -0.73
     Turch
    -0.73
    évaluateur
    -0.72
     JScrollPane
    -0.72
     BitmapFactory
    -0.70
     Lacy
    -0.70
    Birch
    -0.69
    Mako
    -0.69
     OnClickListener
    -0.68
    POSITIVE LOGITS
    mathbb
    1.15
     indeb
    0.70
     defaultstate
    0.70
     newOwner
    0.69
    attenzione
    0.69
     Pind
    0.66
    HasIndex
    0.65
    theless
    0.65
     Wier
    0.64
    IFIER
    0.64
    Activations Density 0.135%

    No Known Activations