© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15136
    Prev
    Next
    INDEX
    Explanations

    terms related to drug delivery systems and their formulations

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

    Drug delivery and release

    np_acts-logits-general · gemini-2.0-flash

    controlled release delivery

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    EDEFAULT
    -0.77
     CreateTagHelper
    -0.72
    CloseOperation
    -0.72
     autorytatywna
    -0.66
    imageshack
    -0.66
    RuleContext
    -0.65
    tività
    -0.61
     الحره
    -0.61
    DATABASES
    -0.59
    AnchorStyles
    -0.59
    POSITIVE LOGITS
     delivery
    1.15
     Delivery
    1.02
    delivery
    0.98
     release
    0.95
    Delivery
    0.94
     deliver
    0.91
     DELIVERY
    0.89
    release
    0.87
     delivering
    0.86
     delivered
    0.84
    Activations Density 1.064%

    No Known Activations