© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10225
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and definitions related to trajectories and spaces in statistical concepts

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

    formal mathematical notation in LaTeX-style, especially dense equations and set/indexed expressions with symbols, subscripts/superscripts, and structured sequences or trajectories.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    mathematical notation describing sets, subsets, or collections of elements with indexed variables.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    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
     nahilalakip
    -0.37
     ker
    -0.35
    ValueStyle
    -0.32
     Ker
    -0.31
    ListTile
    -0.31
     IconData
    -0.31
    AxisAlignment
    -0.30
    areg
    -0.30
     devraient
    -0.29
    props
    -0.29
    POSITIVE LOGITS
    webElementXpaths
    0.62
     betweenstory
    0.60
    setVerticalGroup
    0.56
    parsedMessage
    0.54
     kasarigan
    0.52
     subsets
    0.48
    GMENT
    0.48
     celana
    0.48
    出版年
    0.48
    vrouw
    0.47
    Activations Density 1.333%

    No Known Activations