© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1156
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and specific relationships in equations

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

    mathematical and scientific notation, particularly symbols and exponents.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    mathematical and document formatting elements like page numbers, brackets, equations, and technical notation.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
    PerformLayout
    -0.86
     arşivlendi
    -0.64
     مشين
    -0.58
     تضيفلها
    -0.53
    رشف
    -0.49
     protoimpl
    -0.49
    StoryboardSegue
    -0.48
     <=",
    -0.47
    ParallelGroup
    -0.46
    MathML
    -0.46
    POSITIVE LOGITS
    EndContext
    0.43
    makeText
    0.42
    Autoritní
    0.42
    __).
    0.41
    Външни
    0.40
    ValueStyle
    0.35
    Montserrat
    0.33
     INTERESAR
    0.33
    verifyException
    0.32
     Dickens
    0.32
    Activations Density 5.451%

    No Known Activations