© 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. 16-GEMMASCOPE-RES-16K
    11. 9515
    Prev
    Next
    INDEX
    Explanations

    phrases indicating disbelief or unexpectedness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows words like "never," "knew," or "realize"

    np_acts-logits-general · gemini-2.0-flash

    such, never, understood

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     thừa
    -0.51
     Conſ
    -0.50
    ILLO
    -0.49
     quia
    -0.48
    AutoModerator
    -0.48
     becauſe
    -0.47
     inol
    -0.47
    ähr
    -0.46
     houſe
    -0.45
    TestData
    -0.45
    POSITIVE LOGITS
     tão
    1.11
     such
    1.05
     столь
    1.04
    such
    1.00
    こんなに
    1.00
    這麼
    0.99
    这么
    0.94
    如此
    0.94
     solch
    0.94
     چنین
    0.93
    Activations Density 0.177%

    No Known Activations