© 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. 5-GEMMASCOPE-RES-16K
    11. 474
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "upon" in various contexts

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

    occurrences of the word "upon" in various capitalization forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ing
    -0.98
     I
    -0.76
    4
    -0.73
    -
    -0.71
    8
    -0.71
     or
    -0.69
     B
    -0.69
     G
    -0.68
    3
    -0.67
    1
    -0.66
    POSITIVE LOGITS
     UPON
    2.05
    upon
    2.02
     Upon
    1.85
     upon
    1.82
    Upon
    1.80
     apon
    1.11
     betweenstory
    0.99
     thereupon
    0.96
    estries
    0.94
    rungsseite
    0.93
    Activations Density 0.214%

    No Known Activations