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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6800
    Prev
    Next
    INDEX
    Explanations

    content that describes classifications and groupings within structured data or categories

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

    sentences or passages discussing how things are categorized or divided into parts or groups.

    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
     للمعارف
    -0.52
    rungsseite
    -0.49
     مشين
    -0.47
     iconLine
    -0.47
    Diwedd
    -0.46
     HasFactory
    -0.46
    tinyos
    -0.42
     cwd
    -0.42
     PTSD
    -0.42
    setTextColor
    -0.42
    POSITIVE LOGITS
     categories
    0.64
    divided
    0.60
     divided
    0.59
     divisions
    0.57
     تقسیم
    0.52
     dividing
    0.49
    分为
    0.49
     divide
    0.48
     sub
    0.48
    categories
    0.47
    Activations Density 0.344%

    No Known Activations