© 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. 7588
    Prev
    Next
    INDEX
    Explanations

    references to scientific concepts and measurements related to environmental impact

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

    definite articles "the" followed by nouns, especially when referencing specific entities.

    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
    sizeCache
    -0.53
    edicated
    -0.49
     colspan
    -0.45
    RenderAtEndOf
    -0.45
     kaynağından
    -0.44
    assignments
    -0.41
    excited
    -0.41
    dientemente
    -0.41
    httphttps
    -0.41
     otomatig
    -0.40
    POSITIVE LOGITS
    tanleria
    0.56
     mergeFrom
    0.51
    SBATCH
    0.47
    Gweler
    0.47
    setCellStyle
    0.44
     Вікі
    0.42
     >=",
    0.42
    oredCriteria
    0.42
     Italijani
    0.41
    /*++
    0.40
    Activations Density 0.331%

    No Known Activations