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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 15811
    Prev
    Next
    INDEX
    Explanations

    terms related to quality and accreditation in healthcare standards and practices

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

    ISO, quality, and standards

    np_acts-logits-general · gemini-2.0-flash

    quality, accreditation, and standards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ftagPool
    -0.61
     souri
    -0.51
     façons
    -0.50
     Waterways
    -0.50
     SwiftUI
    -0.49
    ี่ย
    -0.49
    AsUp
    -0.49
     taxed
    -0.48
     treas
    -0.48
    οιν
    -0.46
    POSITIVE LOGITS
     ISO
    1.03
     Quality
    0.87
     quality
    0.83
    Quality
    0.79
    QUALITY
    0.76
    quality
    0.72
     QUALITY
    0.72
    UnsafeEnabled
    0.71
    ISO
    0.70
    KURZBESCHREIBUNG
    0.65
    Activations Density 0.067%

    No Known Activations