© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 3641
    Prev
    Next
    INDEX
    Explanations

    phrases related to data security and privacy policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     slike
    -0.43
    晚了
    -0.43
    到的
    -0.43
    ,
    -0.42
    TabStop
    -0.41
     and
    -0.40
     rekening
    -0.40
     aside
    -0.40
     all
    -0.40
    出的
    -0.39
    POSITIVE LOGITS
     kasarigan
    0.95
     autorytatywna
    0.95
     الحره
    0.94
     المعيارى
    0.88
    "]').
    0.82
    ']").
    0.82
    ConstraintMaker
    0.79
    Autoritní
    0.79
    出版年
    0.79
     otomatig
    0.78
    Activations Density 0.509%

    No Known Activations