© 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. 20-GEMMASCOPE-RES-16K
    11. 11182
    Prev
    Next
    INDEX
    Explanations

    keywords related to scientific and research concepts

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

    lists of items separated by commas with "and" before the final item.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered 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
    httphttps
    -0.62
    addCriterion
    -0.61
    cticut
    -0.58
    AttributeSet
    -0.56
    rungsseite
    -0.56
    URLException
    -0.56
     חיצוניים
    -0.54
     ब्रेकडाउन
    -0.54
     betweenstory
    -0.54
    DockStyle
    -0.54
    POSITIVE LOGITS
     etc
    0.60
    etc
    0.51
     all
    0.47
     various
    0.46
    various
    0.44
     among
    0.44
     Various
    0.43
     Etc
    0.42
     Stirn
    0.41
    Various
    0.40
    Activations Density 0.208%

    No Known Activations