© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 11464
    Prev
    Next
    INDEX
    Explanations

    references to dosage and formulations in medical or dietary contexts

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

    Dosage, formulation, or specifications

    np_acts-logits-general · gemini-2.0-flash

    dosage and formulation quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Италијани
    -0.81
    ThroughAttribute
    -0.70
    expandindo
    -0.69
     Roskov
    -0.68
    parsedMessage
    -0.68
     otomatig
    -0.68
     يتيمه
    -0.66
    contentLoaded
    -0.65
    ArrowToggle
    -0.63
     Савезне
    -0.62
    POSITIVE LOGITS
     format
    0.54
    pH
    0.54
     pH
    0.52
     altitudes
    0.52
     salinity
    0.51
    viewType
    0.51
     itinerary
    0.50
     topology
    0.50
     polarity
    0.50
     layout
    0.49
    Activations Density 1.463%

    No Known Activations