© 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. 8-GEMMASCOPE-RES-16K
    11. 8939
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Paul."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Anſ
    -1.04
     pleaſure
    -1.01
     preſent
    -0.98
     Bli
    -0.98
     Ibis
    -0.96
     Reſ
    -0.89
     ſy
    -0.88
     Bertie
    -0.88
     Monfieur
    -0.87
     iſt
    -0.86
    POSITIVE LOGITS
     Paul
    1.47
    Paul
    1.27
     PAUL
    1.12
    PAUL
    0.97
     Paulson
    0.96
     paul
    0.93
    paul
    0.93
     Paulus
    0.91
     Paulina
    0.85
     Paula
    0.77
    Activations Density 0.047%

    No Known Activations