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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 45829
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to medication and treatment adherence

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

    medication adherence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    عرِّف
    -0.52
    TargetApi
    -0.52
    msgTypes
    -0.50
    ClientRect
    -0.48
    contentLoaded
    -0.47
    webElementXpaths
    -0.47
    BuilderFactory
    -0.47
    Personendaten
    -0.45
    Werdegang
    -0.44
    modb
    -0.44
    POSITIVE LOGITS
     Consistency
    0.49
    Aholisi
    0.42
     consistency
    0.41
     maintenance
    0.40
     Maintenance
    0.39
    discipline
    0.39
    mybatisplus
    0.39
    Consistency
    0.38
    prepareStatement
    0.37
    뀜
    0.37
    Activations Density 0.041%

    No Known Activations