© 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. 20-GEMMASCOPE-RES-16K
    6. 6844
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "ring" and its variations

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

    following "Ring" or "ring"

    np_acts-logits-general · gemini-2.0-flash

    ring or ding followed by a name or word

    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
    存于互联网档案馆
    -0.70
    abetes
    -0.63
    ArgsConstructor
    -0.62
    PerformLayout
    -0.61
    epam
    -0.60
    Czytaj
    -0.58
    Бахар
    -0.58
    leece
    -0.57
     Вікіпе
    -0.56
    surface
    -0.56
    POSITIVE LOGITS
     RING
    0.68
    Ding
    0.67
    Ing
    0.67
     Ing
    0.65
    tone
    0.64
    gggg
    0.64
     Ring
    0.64
    ggg
    0.63
     cing
    0.62
    dings
    0.61
    Activations Density 0.124%

    No Known Activations