© 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. 1358
    Prev
    Next
    INDEX
    Explanations

    references to the term "cro" and its variations, which appear to relate to crocodiles and geographical terms

    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
     kasarigan
    -0.65
     Imágenes
    -0.61
    StoreMessageInfo
    -0.61
    はじめに
    -0.61
     sumpay
    -0.58
    stdc
    -0.58
     Pati
    -0.56
    Pati
    -0.56
    مصادر
    -0.55
    betic
    -0.54
    POSITIVE LOGITS
     Cro
    0.87
     CRO
    0.85
    Cro
    0.79
    Xna
    0.69
     cro
    0.68
    posedge
    0.68
     kro
    0.64
    kro
    0.63
    CRO
    0.61
    cro
    0.61
    Activations Density 0.094%

    No Known Activations