© 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. 1934
    Prev
    Next
    INDEX
    Explanations

    terms related to the assessment of medical conditions or treatments at early stages

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

    phrases related to time progression or temporal descriptions.

    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
    /**
    -0.48
     surla
    -0.47
    enumi
    -0.44
     intStringLen
    -0.43
     Govern
    -0.43
    lillah
    -0.43
     Governor
    -0.42
    pompa
    -0.42
     popu
    -0.41
    /*
    -0.41
    POSITIVE LOGITS
    まだ
    0.61
    まだまだ
    0.60
     immature
    0.57
    はまだ
    0.56
     unfinished
    0.50
     chưa
    0.50
     nascent
    0.50
    未
    0.49
     vielä
    0.49
     todavía
    0.48
    Activations Density 0.275%

    No Known Activations