© 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. 12130
    Prev
    Next
    INDEX
    Explanations

    medical terms related to pharmacology and drug interactions

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

    scientific or medical terminology involving chemical compounds, drugs, and pharmaceutical research details.

    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
     kebun
    -0.52
    []):
    -0.52
    ')):
    -0.51
     increí
    -0.50
     Normdatei
    -0.50
    Дереккөздер
    -0.50
    AnchorStyles
    -0.50
     kiện
    -0.49
     vklju
    -0.49
    bibinfo
    -0.47
    POSITIVE LOGITS
    romycin
    0.52
    anthin
    0.48
    amethasone
    0.47
     Alcohol
    0.47
    amycin
    0.45
     ſte
    0.45
     Cocaine
    0.44
     hydrochloride
    0.43
    veratrol
    0.43
     dioxide
    0.43
    Activations Density 1.007%

    No Known Activations