© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 2412
    Prev
    Next
    INDEX
    Explanations

    references to the concept of quality in various contexts

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

    mentions of "quality" in various contexts, such as service quality, product quality, or performance quality.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
     from
    -0.40
     in
    -0.39
     who
    -0.38
     lets
    -0.38
     recent
    -0.37
     Anhäng
    -0.36
     Barrera
    -0.36
     next
    -0.35
     on
    -0.35
    tick
    -0.35
    POSITIVE LOGITS
    Quality
    1.34
     Quality
    1.29
    quality
    1.22
    QUALITY
    1.21
     QUALITY
    1.20
     quality
    1.19
     Qualität
    0.99
     kwaliteit
    0.96
    qualität
    0.94
    Calidad
    0.94
    Activations Density 0.048%

    No Known Activations