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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11206
    Prev
    Next
    INDEX
    Explanations

    phrases related to quality assessment

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

    product or data "quality"

    np_acts-logits-general · gemini-2.0-flash

    quality

    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-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
     propOrder
    -0.47
    iedenis
    -0.45
     Unidas
    -0.42
    agem
    -0.42
     Khanna
    -0.41
     nonatomic
    -0.41
     INSTANCE
    -0.41
    arote
    -0.40
    pesas
    -0.40
    Clue
    -0.40
    POSITIVE LOGITS
     quality
    3.20
    quality
    2.75
     Quality
    2.60
    Quality
    2.58
     QUALITY
    2.57
    QUALITY
    2.41
     qualité
    2.35
     calidad
    2.27
     qualidade
    2.21
     qualità
    2.21
    Activations Density 0.215%

    No Known Activations