© 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-2-2B
    4. Residual Stream - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 329
    Prev
    Next
    INDEX
    Explanations

    specific information regarding medical treatment dosages and schedules

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

    references to dosages and injections related to medication

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

    daily and frequency

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    ctives
    -0.53
    SourceChecksum
    -0.46
     distanciation
    -0.46
     للاسماء
    -0.46
    \{\\
    -0.46
    nshaw
    -0.46
     Bateman
    -0.45
     IMC
    -0.45
     ModelExpression
    -0.45
     substring
    -0.45
    POSITIVE LOGITS
     daily
    2.02
    daily
    1.70
    Daily
    1.54
     nightly
    1.52
     Daily
    1.51
     DAILY
    1.50
     everyday
    1.38
     quotidienne
    1.36
    DAILY
    1.33
     morning
    1.33
    Activations Density 0.179%

    No Known Activations