© 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. 7-GEMMASCOPE-RES-16K
    11. 6923
    Prev
    Next
    INDEX
    Explanations

    phrases that contain the word "which" indicating a detailed explanation or elaboration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IsPostBack
    -0.88
     myſelf
    -0.86
    AlterField
    -0.80
    Geplaatst
    -0.73
    RegressionTest
    -0.71
    expandindo
    -0.71
     ――――
    -0.71
    ^(@)
    -0.71
     cdti
    -0.70
     ―――――
    -0.69
    POSITIVE LOGITS
     Which
    0.81
    Which
    0.79
     vilket
    0.70
    googleapis
    0.69
     which
    0.67
     thankfully
    0.65
     WHICH
    0.63
     is
    0.63
    which
    0.63
    Meaning
    0.58
    Activations Density 0.212%

    No Known Activations