© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 49
    Prev
    Next
    INDEX
    Explanations

    terms related to health assessments and healthcare recommendations

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

    Regularly scheduled appointments

    np_acts-logits-general · gemini-2.0-flash

    periodic health screenings

    np_acts-logits-general · gemini-2.5-flash-lite

    The highlighted tokens appear in healthcare and procedural contexts, marking phrases related to obtaining or receiving medical services, undergoing treatments, or attending appointments. They serve as connectors or action verbs that bridge the subject with a medical intervention or visit.

    eleuther_acts_top20 · claude-4-5-haikuTriggered by @kparkhamchuk
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    GOTREF
    -0.79
    tagHelperRunner
    -0.72
     Италијани
    -0.59
    HomeAsUpEnabled
    -0.58
    fjspx
    -0.58
    rativo
    -0.51
    rungsseite
    -0.50
     للمعارف
    -0.49
     Erz
    -0.49
    PreferredItem
    -0.48
    POSITIVE LOGITS
     checkup
    1.16
     annual
    1.11
     yearly
    1.08
     routine
    1.06
     inspection
    1.05
    Annual
    1.04
     screenings
    1.04
     screening
    1.02
     examinations
    1.02
     Periodic
    1.00
    Activations Density 0.417%

    No Known Activations