© 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 - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 2070
    Prev
    Next
    INDEX
    Explanations

    words related to cultural or religious texts and their significance

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

    Japanese text or names

    np_acts-logits-general · gemini-2.0-flash

    Japanese names ending in 〇沢 or 〇谷

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sp
    -0.48
     scheme
    -0.46
     check
    -0.45
     spot
    -0.45
     rec
    -0.44
    ValueStyle
    -0.43
     overall
    -0.43
     rate
    -0.43
     short
    -0.42
    Import
    -0.42
    POSITIVE LOGITS
     يتيمه
    1.16
    transQ
    0.89
    thâu
    0.84
    DoubleQuotes
    0.82
    קישורים
    0.77
     للمعارف
    0.75
    حوالہ
    0.74
    下载附件
    0.73
     esternos
    0.73
    ніципа
    0.69
    Activations Density 0.100%

    No Known Activations