© 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. 2-GEMMASCOPE-RES-16K
    11. 8908
    Prev
    Next
    INDEX
    Explanations

    negative values associated with data attributes or toggles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Houſe
    -1.07
     ſeveral
    -1.06
     Monfieur
    -1.04
     myſelf
    -0.99
     houſe
    -0.98
     ſta
    -0.96
     Theſe
    -0.95
     ſever
    -0.94
     ſhe
    -0.93
     themſelves
    -0.92
    POSITIVE LOGITS
    machten
    0.56
    Citation
    0.54
    τουργ
    0.51
    <#
    0.50
    τως
    0.49
    begin
    0.48
     "__
    0.47
    存于互联网档案馆
    0.47
    ました
    0.47
    erobic
    0.46
    Activations Density 0.185%

    No Known Activations