© 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. 2-GEMMASCOPE-RES-16K
    11. 4244
    Prev
    Next
    INDEX
    Explanations

    references to scientific and technical concepts related to medicinal compounds and procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مشين
    -0.93
     Belinda
    -0.85
    PositiveButton
    -0.81
     charité
    -0.80
     Coe
    -0.80
     Hage
    -0.78
     NOK
    -0.78
     transfé
    -0.78
    NOK
    -0.77
     Seton
    -0.77
    POSITIVE LOGITS
    Bron
    0.81
     Gre
    0.77
     DRA
    0.77
     Cram
    0.76
     Brou
    0.75
     Bron
    0.75
     Brownian
    0.75
     Drew
    0.75
    Cros
    0.73
    brou
    0.71
    Activations Density 8.126%

    No Known Activations