© 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. 13013
    Prev
    Next
    INDEX
    Explanations

    terms related to healthcare and organizational structures

    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
     milliers
    -0.82
    thousands
    -0.79
     muchos
    -0.77
     utafitiHapana
    -0.75
    ม้
    -0.74
     Thousands
    -0.74
     thousands
    -0.74
     everywhere
    -0.73
    hundreds
    -0.73
     duiz
    -0.73
    POSITIVE LOGITS
    分别是
    1.55
     namely
    1.41
    分別
    1.38
    分别
    1.31
     respectively
    1.29
    respectively
    1.16
    namely
    1.13
     each
    1.09
     apiece
    1.08
    一个是
    1.05
    Activations Density 0.599%

    No Known Activations