© 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. 3-GEMMASCOPE-RES-16K
    11. 5879
    Prev
    Next
    INDEX
    Explanations

    proper nouns and proper names related to people and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tal
    -0.72
    Hutch
    -0.68
    Collegamenti
    -0.68
    Lato
    -0.67
     incomplète
    -0.67
    Glo
    -0.65
    Daphne
    -0.65
    kter
    -0.64
    drücke
    -0.64
    cadilly
    -0.64
    POSITIVE LOGITS
     Iain
    1.02
     IAA
    0.94
     Beaumont
    0.90
    Iain
    0.90
     Leia
    0.89
     Jai
    0.89
     Miel
    0.88
     CEE
    0.88
    Cair
    0.85
     Kei
    0.84
    Activations Density 1.598%

    No Known Activations