© 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-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 86
    Prev
    Next
    INDEX
    Explanations

    references to structured data types and manipulation

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

    programmatic instructions related to data manipulation and structure

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

    finding index or position

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    ็จ
    -0.52
    ambo
    -0.51
    ReadKey
    -0.45
    KELEY
    -0.45
     مسؤول
    -0.45
    otrop
    -0.44
    SizeF
    -0.43
     tölt
    -0.43
    各样的
    -0.42
    以外は
    -0.42
    POSITIVE LOGITS
     jScrollPane
    0.75
     indexOf
    0.69
    IndexOf
    0.67
    findIndex
    0.63
    getColumnIndex
    0.63
     INDEX
    0.62
    ьаж
    0.61
    indexOf
    0.61
     index
    0.60
    $_['
    0.59
    Activations Density 0.034%

    No Known Activations