© 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-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 10578
    Prev
    Next
    INDEX
    Explanations

    characters or symbols related to mathematical expressions or equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rawQuery
    -0.47
    fromJson
    -0.47
    ガニック
    -0.46
    kta
    -0.46
    懐
    -0.44
    ̍
    -0.43
     Motley
    -0.43
    xaml
    -0.43
     Joaquim
    -0.43
    onAttach
    -0.43
    POSITIVE LOGITS
    الثة
    0.86
     ketiga
    0.83
    ❸
    0.83
    .³
    0.80
     triad
    0.78
     terceiro
    0.76
    3
    0.76
     troisième
    0.75
     第三
    0.74
    треть
    0.73
    Activations Density 1.129%

    No Known Activations