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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 5140
    Prev
    Next
    INDEX
    Explanations

    comparative phrases regarding test results in scientific studies

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

    scientific statistical data and numerical comparisons, particularly in medical or research contexts.

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

    comparative statements in scientific writing, especially phrases involving "higher than" or similar comparisons.

    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
    
    -0.65
    enumi
    -0.64
    InjectAttribute
    -0.63
    :✨
    -0.63
    LookAnd
    -0.61
     houſe
    -0.60
     Houſe
    -0.59
     SWR
    -0.59
     ſont
    -0.59
     gsm
    -0.59
    POSITIVE LOGITS
     nearly
    0.45
     geringe
    0.42
     geringen
    0.42
     differed
    0.39
     Nearly
    0.38
     slight
    0.37
     glede
    0.36
     consistently
    0.36
     almost
    0.36
     hampir
    0.36
    Activations Density 1.365%

    No Known Activations