© 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. 21-GEMMASCOPE-RES-16K
    11. 2513
    Prev
    Next
    INDEX
    Explanations

    locations and elements related to news reporting, medical emergencies, and data transmission

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     FetchType
    -0.78
     terhadap
    -0.68
    égard
    -0.67
    sizeCache
    -0.59
     compared
    -0.56
    HttpGet
    -0.55
    Fprintf
    -0.54
    compared
    -0.53
    Especially
    -0.53
    UNDLE
    -0.52
    POSITIVE LOGITS
     via
    0.92
     terdekat
    0.73
     whence
    0.71
     vía
    0.68
     VIA
    0.66
    去了
    0.65
     where
    0.62
     aussitôt
    0.62
     definitivo
    0.62
     tramite
    0.61
    Activations Density 0.656%

    No Known Activations