© 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-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 12546
    Prev
    Next
    INDEX
    Explanations

    specific medical terminology and conditions related to drug exposure and its effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.71
    hyrchwyd
    -0.63
     figliu
    -0.61
    RegressionTest
    -0.59
     betweenstory
    -0.59
    Jîn
    -0.58
     greateſt
    -0.56
     hanem
    -0.56
    PreInfinity
    -0.55
     hunne
    -0.55
    POSITIVE LOGITS
     חיצוניים
    0.73
    たまた
    0.61
     كومونز
    0.61
     kasarigan
    0.60
    تقاوى
    0.60
    ZIE
    0.58
    üyada
    0.55
     שוליים
    0.54
    displayquote
    0.54
    uronic
    0.54
    Activations Density 1.352%

    No Known Activations