© 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. 5092
    Prev
    Next
    INDEX
    Explanations

    sequences of incrementing and decrementing operations

    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
     O
    -0.63
     g
    -0.57
    umb
    -0.52
     h
    -0.51
     in
    -0.51
     '
    -0.51
     nas
    -0.50
     En
    -0.50
     An
    -0.49
     tra
    -0.49
    POSITIVE LOGITS
     autorytatywna
    1.08
    enumi
    1.02
     myſelf
    1.02
     pleaſure
    1.02
     ExecuteAsync
    1.00
     fevere
    0.99
    Hozzáférés
    0.97
     Monfieur
    0.94
     itſelf
    0.92
     Jefus
    0.90
    Activations Density 0.035%

    No Known Activations