© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 10874
    Prev
    Next
    INDEX
    Explanations

    Chinese phrases related to content submission and personal information

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

    words related to medical conditions and health-related terminology.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    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
    expandindo
    -0.55
     okuyayım
    -0.55
    setVerticalGroup
    -0.48
    ferent
    -0.47
    ỡng
    -0.47
    getStringExtra
    -0.46
     betweenstory
    -0.46
    findpost
    -0.45
    
    -0.45
     Ally
    -0.44
    POSITIVE LOGITS
     is
    0.52
     kehadiran
    0.48
     względu
    0.48
    zuführen
    0.48
     has
    0.48
    getreten
    0.46
     μπορεί
    0.46
     móg
    0.46
     kepem
    0.45
    既
    0.45
    Activations Density 0.054%

    No Known Activations