© 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. 4716
    Prev
    Next
    INDEX
    Explanations

    attributes related to XML documents and their structure

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

    technical terminology related to XML and computer programming.

    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
     AssemblyCulture
    -0.96
     '\\;'
    -0.86
    richTextPanel
    -0.83
    DockStyle
    -0.81
     للمعارف
    -0.77
     Exactos
    -0.75
     surla
    -0.75
    SBATCH
    -0.73
     typelib
    -0.71
    HideFlags
    -0.71
    POSITIVE LOGITS
    De
    0.36
     Lud
    0.34
    doc
    0.33
    Val
    0.32
     hæ
    0.31
     Est
    0.30
    ”
    0.30
    Tra
    0.30
    Zo
    0.30
     c
    0.30
    Activations Density 0.540%

    No Known Activations