© 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. 8441
    Prev
    Next
    INDEX
    Explanations

    multilingual references and expressions related to personal background and experiences

    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
    BP
    -0.43
     brig
    -0.40
     TextAppearance
    -0.40
     accomod
    -0.40
    stle
    -0.40
     ponts
    -0.37
    LT
    -0.36
     ReactDOM
    -0.36
    們
    -0.36
     paramInt
    -0.35
    POSITIVE LOGITS
     <>",
    0.64
     okuyayım
    0.58
    :✨
    0.57
     Infórmanos
    0.57
    bibinfo
    0.56
    bibfield
    0.55
    SharedCtor
    0.55
    BufferException
    0.54
    balleur
    0.51
    حياتها
    0.50
    Activations Density 0.161%

    No Known Activations