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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4672
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "word" and "language."

    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
    ]-->
    -0.68
    ‍♂️
    -0.66
     Shreve
    -0.62
     betrek
    -0.61
    ‍♀️
    -0.60
    Hauptartikel
    -0.58
    raiser
    -0.58
    borns
    -0.57
    IContainer
    -0.57
    ⓧ
    -0.57
    POSITIVE LOGITS
     Word
    0.93
     WORD
    0.91
     Words
    0.88
     words
    0.87
     word
    0.86
     WORDS
    0.81
    Word
    0.80
    Words
    0.75
     palabras
    0.71
    WORD
    0.69
    Activations Density 0.142%

    No Known Activations