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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15993
    Prev
    Next
    INDEX
    Explanations

    phrases associated with quality and assessment of samples or services

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

    preceding "quality"

    np_acts-logits-general · gemini-2.0-flash

    quality of DNA or reads

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BorderRadius
    -0.41
     feroit
    -0.40
    下载附件
    -0.40
    Билгалдахарш
    -0.37
     المعيارى
    -0.35
     presidencial
    -0.34
    XmlRootElement
    -0.34
    więcej
    -0.33
     dumne
    -0.32
     EdgeInsets
    -0.32
    POSITIVE LOGITS
     quality
    3.16
    quality
    2.84
    Quality
    2.66
     Quality
    2.58
     QUALITY
    2.50
     calidad
    2.44
     qualidade
    2.41
     Qualität
    2.39
     qualité
    2.36
     qualità
    2.30
    Activations Density 0.378%

    No Known Activations