© 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. 4-GEMMASCOPE-RES-16K
    11. 11782
    Prev
    Next
    INDEX
    Explanations

    references to maximizing effort or potential in various contexts

    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
    +#+
    -0.69
    LookAnd
    -0.68
     Audiodateien
    -0.66
    TintMode
    -0.62
    icza
    -0.57
     gehö
    -0.56
     autorytatywna
    -0.56
    atrième
    -0.55
    WithIdentifier
    -0.54
    untamente
    -0.53
    POSITIVE LOGITS
    try
    0.74
     möglichst
    0.72
    尽可能
    0.69
    できるだけ
    0.66
    なるべく
    0.66
     try
    0.65
    尽量
    0.64
     tries
    0.63
     سعی
    0.62
     Try
    0.61
    Activations Density 0.369%

    No Known Activations