© 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-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 9399
    Prev
    Next
    INDEX
    Explanations

    references to quality in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wege
    -0.54
     emerging
    -0.52
     Aspekte
    -0.52
    elif
    -0.49
     Otherwise
    -0.49
     daunting
    -0.48
     otherwise
    -0.48
     plumas
    -0.48
    Otherwise
    -0.48
    STEPS
    -0.48
    POSITIVE LOGITS
     quality
    1.36
     Quality
    1.25
    quality
    1.20
    Quality
    1.17
     QUALITY
    1.09
    QUALITY
    1.03
     kwaliteit
    0.97
     qualité
    0.96
     qualidade
    0.93
     calidad
    0.92
    Activations Density 0.273%

    No Known Activations