© 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. 4-GEMMASCOPE-RES-16K
    11. 2932
    Prev
    Next
    INDEX
    Explanations

    mentions of "people."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XSSF
    -0.76
     zimowe
    -0.74
    іод
    -0.74
     remporté
    -0.74
     navideños
    -0.71
     gius
    -0.71
     '\\;'
    -0.71
    Приятного
    -0.71
     cleft
    -0.71
     Selon
    -0.71
    POSITIVE LOGITS
     people
    2.56
    people
    2.38
    People
    2.35
     People
    2.33
     PEOPLE
    2.17
    PEOPLE
    2.05
     peoples
    1.50
     peop
    1.45
     ppl
    1.43
     Peoples
    1.36
    Activations Density 0.113%

    No Known Activations