© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 9108
    Prev
    Next
    INDEX
    Explanations

    words and characters in diverse languages and scripts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     การ์ตูน
    -0.68
     erop
    -0.67
     Statt
    -0.66
     ente
    -0.65
     Theſe
    -0.60
    ώρα
    -0.58
     τὸ
    -0.57
     Wegen
    -0.57
     Việt
    -0.56
    Autoritní
    -0.55
    POSITIVE LOGITS
     प
    0.96
     ا
    0.96
     ब
    0.94
    UpInside
    0.93
     א
    0.90
     پ
    0.89
     ग
    0.89
     म
    0.89
     enää
    0.87
     löytyy
    0.85
    Activations Density 0.040%

    No Known Activations