© 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. 19-GEMMASCOPE-RES-16K
    11. 1609
    Prev
    Next
    INDEX
    Explanations

    phrases focused on comfort, care, and efficiency in various contexts, particularly regarding healthcare and environmental considerations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     suddenly
    -0.73
     transfieras
    -0.71
     plötzlich
    -0.69
    suddenly
    -0.69
    Suddenly
    -0.61
     Suddenly
    -0.60
    InitVars
    -0.55
     soudain
    -0.54
     tiba
    -0.52
    meo
    -0.52
    POSITIVE LOGITS
     möglichst
    1.91
    尽可能
    1.58
    できるだけ
    1.45
    なるべく
    1.42
     максимально
    1.31
    尽量
    1.30
     maximize
    1.30
     maximized
    1.30
     maximizing
    1.22
     maximizes
    1.21
    Activations Density 0.447%

    No Known Activations