© 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. 1-GEMMASCOPE-RES-16K
    11. 3727
    Prev
    Next
    INDEX
    Explanations

    repetitive mentions of the term "these."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    addComponent
    -0.54
    गर
    -0.52
     있다
    -0.51
     was
    -0.50
    vel
    -0.50
    wertes
    -0.49
    ẤT
    -0.49
    PathVariable
    -0.49
    volles
    -0.49
    nextSibling
    -0.49
    POSITIVE LOGITS
     these
    3.74
    these
    3.40
    These
    3.18
     These
    3.11
     THESE
    2.99
    这些
    2.45
    這些
    2.41
    Эти
    2.28
    Estos
    2.27
    これらの
    2.24
    Activations Density 0.126%

    No Known Activations