© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 123035
    Prev
    Next
    INDEX
    Explanations

    terms related to pharmacy benefit management and medication adherence

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

    pharmacy and pharmacists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    sphase
    -0.38
    varlak
    -0.37
    토
    -0.31
     conclure
    -0.30
     Vereinigung
    -0.29
     satisfaire
    -0.29
     '
    -0.29
    коро
    -0.29
    agonia
    -0.28
    presas
    -0.28
    POSITIVE LOGITS
     pharmacy
    1.03
     pharmacist
    1.03
    Pharmacy
    1.02
     Pharmacy
    1.02
     pharmacists
    0.99
    pharmacy
    0.97
     pharmacies
    0.94
     pharmacie
    0.77
     farmacé
    0.76
    Medication
    0.74
    Activations Density 0.018%

    No Known Activations