© 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. 11752
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical structures and definitions

    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
    rich
    -0.56
    LETE
    -0.53
     rich
    -0.50
     Deep
    -0.48
    tite
    -0.47
    IVAN
    -0.47
    krat
    -0.47
    ULLY
    -0.47
    kier
    -0.45
    loff
    -0.45
    POSITIVE LOGITS
    AddTagHelper
    1.13
     autorytatywna
    1.07
    transQ
    0.92
    DockStyle
    0.91
    HideFlags
    0.89
    Lähteet
    0.88
     StatelessWidget
    0.86
    webElementXpaths
    0.85
    WithIOException
    0.84
     kasarigan
    0.82
    Activations Density 1.097%

    No Known Activations