© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 11387
    Prev
    Next
    INDEX
    Explanations

    information related to medication dosages and clinical trial protocols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oa̍t
    -0.45
     ffilmiau
    -0.45
    éroport
    -0.40
     explosives
    -0.38
    conde
    -0.37
    ┫
    -0.36
     fuels
    -0.34
    mose
    -0.34
     Zucker
    -0.34
    exhaus
    -0.34
    POSITIVE LOGITS
     dosage
    1.24
     dose
    1.12
     dosages
    1.11
     doses
    1.10
     dosing
    1.06
     dosis
    1.03
     Dosage
    1.03
    Dosage
    1.02
     Dosis
    0.96
     Dose
    0.96
    Activations Density 1.132%

    No Known Activations