© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 20-GEMMASCOPE-RES-16K
    11. 14750
    Prev
    Next
    INDEX
    Explanations

    topics related to various uses and effects, particularly in the context of health, technology, and community

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Preceding words of "use," "side," or "birth"

    np_acts-logits-general · gemini-2.0-flash

    common phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jarige
    -0.62
     Majefty
    -0.62
    อ้างอิง
    -0.62
     reaſon
    -0.59
    タイプの
    -0.57
    Referințe
    -0.57
    pecific
    -0.56
    ]),
    -0.56
     LIRE
    -0.56
    readystatechange
    -0.55
    POSITIVE LOGITS
    
    0.59
     tartalomajánló
    0.56
     gawas
    0.53
     otomatig
    0.52
     JLabel
    0.50
    AddTagHelper
    0.48
    IVEREF
    0.47
    oint
    0.47
    Worse
    0.46
     JButton
    0.46
    Activations Density 1.180%

    No Known Activations