© 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. 3382
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports events and their statistics

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

    specific numerical ranges or dates, particularly years and statistical data points.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered 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
     tonight
    -0.43
     today
    -0.39
     demain
    -0.38
     đang
    -0.37
    これから
    -0.37
    fromnode
    -0.37
     сегодня
    -0.36
     todays
    -0.36
     дописавши
    -0.36
     heute
    -0.35
    POSITIVE LOGITS
     damals
    0.62
    当时
    0.61
     damaligen
    0.60
    那时候
    0.60
    當時
    0.58
    那时
    0.57
     was
    0.57
     fjor
    0.57
    当时的
    0.56
    IndentedString
    0.56
    Activations Density 0.340%

    No Known Activations