© 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. 1-GEMMASCOPE-RES-16K
    11. 6610
    Prev
    Next
    INDEX
    Explanations

    specific references to scientific concepts and terms within a medical or technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awtextra
    -0.64
     transfieras
    -0.64
     Linder
    -0.58
     дописавши
    -0.58
     ExecuteAsync
    -0.58
    zuki
    -0.58
     nakalista
    -0.57
    cookieParser
    -0.56
    abaza
    -0.56
    Boh
    -0.56
    POSITIVE LOGITS
     dice
    0.65
     penetrate
    0.64
     BLE
    0.61
     vectorielles
    0.60
     accum
    0.59
     Accum
    0.59
    jScrollPane
    0.59
     cricket
    0.59
     penetrates
    0.59
    Personensuche
    0.57
    Activations Density 2.348%

    No Known Activations