Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 4395
    Prev
    Next
    INDEX
    Explanations

    words related to pharmaceutical compositions and drug delivery systems

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

    Pharmaceutical formulations or drug delivery

    np_acts-logits-general · gemini-2.0-flash

    pharmaceutical drug formulations and delivery

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ProtoMessage
    -0.86
    RuleContext
    -0.77
     defaultstate
    -0.76
    CloseOperation
    -0.74
    uxxxx
    -0.74
    interopRequire
    -0.69
    rrggbb
    -0.69
     дописавши
    -0.68
    MigrationBuilder
    -0.68
     typelib
    -0.67
    POSITIVE LOGITS
     delivery
    0.77
     formulation
    0.74
     Formulation
    0.72
     Delivery
    0.71
    Formulation
    0.70
     release
    0.67
     sustained
    0.66
    delivery
    0.66
     drug
    0.65
     formulations
    0.64
    Activations Density 0.849%

    No Known Activations