© 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. 7775
    Prev
    Next
    INDEX
    Explanations

    sports-related terms and results, particularly in the context of tournaments and matches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    richTextPanel
    -0.68
     للاسماء
    -0.61
     ainfi
    -0.59
     zoude
    -0.59
    rungsseite
    -0.57
    antMatchers
    -0.57
    Filmografie
    -0.54
    Perman
    -0.54
     Perman
    -0.54
     feroit
    -0.54
    POSITIVE LOGITS
     outer
    0.35
     smo
    0.35
     oppose
    0.35
     late
    0.34
     sequence
    0.33
     court
    0.33
     shouted
    0.33
    .*")]
    0.32
     kont
    0.32
     Kont
    0.32
    Activations Density 0.019%

    No Known Activations