© 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 - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 96965
    Prev
    Next
    INDEX
    Explanations

    pharmacological terms and concepts related to administration and dosage in medical contexts

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

    administered, prescribed, given, ingestion

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    featureID
    -0.68
     typelib
    -0.55
     AssemblyProduct
    -0.54
    keyColumn
    -0.54
     مشين
    -0.53
     للمعارف
    -0.52
    UnsafeEnabled
    -0.52
    webElementXpaths
    -0.51
     الحره
    -0.50
    fjspx
    -0.50
    POSITIVE LOGITS
     delivered
    0.33
     metic
    0.33
    Carreira
    0.31
     exact
    0.31
     Classification
    0.30
    📐
    0.30
    franch
    0.30
     Delivery
    0.30
     kepad
    0.29
     sona
    0.29
    Activations Density 0.200%

    No Known Activations