© 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. 18-GEMMASCOPE-RES-16K
    11. 464
    Prev
    Next
    INDEX
    Explanations

    references to quality and craftsmanship in products

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

    "quality" or related concepts

    np_acts-logits-general · gemini-2.0-flash

    quality of build

    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
    出版年
    -0.62
     незавершена
    -0.59
    itespace
    -0.57
    RenderAtEndOf
    -0.56
    adden
    -0.56
     busiest
    -0.53
    uchtet
    -0.51
    Билгалдахарш
    -0.51
    MMdd
    -0.51
     dode
    -0.50
    POSITIVE LOGITS
     quality
    2.73
    quality
    2.38
     Quality
    2.30
    Quality
    2.29
     QUALITY
    2.25
    QUALITY
    2.11
     calidad
    2.02
     qualité
    1.94
     qualidade
    1.91
     Qualität
    1.90
    Activations Density 0.228%

    No Known Activations