© 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. 18-GEMMASCOPE-RES-16K
    11. 6165
    Prev
    Next
    INDEX
    Explanations

    concepts related to software updates and user actions in a digital environment

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

    followed by adverbs of manner

    np_acts-logits-general · gemini-2.0-flash

    removed quickly, revoke anytime

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hauptsächlich
    -0.51
    phens
    -0.50
    primarily
    -0.49
     primarily
    -0.49
    敢
    -0.48
     سعی
    -0.48
    主要是
    -0.48
     głównie
    -0.48
     Unable
    -0.47
     yoksa
    -0.47
    POSITIVE LOGITS
     fácilmente
    1.46
     easily
    1.41
     facilmente
    1.34
    ได้
    1.29
    easily
    1.25
     facilement
    1.21
     anytime
    1.17
     Easily
    1.03
    Easily
    1.00
     tranquila
    0.97
    Activations Density 1.013%

    No Known Activations