© 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. 7-GEMMASCOPE-RES-16K
    11. 9081
    Prev
    Next
    INDEX
    Explanations

    terms and references related to the geography, languages, and cultural identity of Papua New Guinea and the surrounding Pacific Islands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monfieur
    -1.11
     Majefty
    -0.94
    ſelf
    -0.94
    ſelves
    -0.93
     itſelf
    -0.93
     leaſt
    -0.92
    eseorang
    -0.91
     myſelf
    -0.90
     Jefus
    -0.89
     houſe
    -0.88
    POSITIVE LOGITS
    Fiji
    0.54
     N
    0.50
     f
    0.49
     F
    0.47
     Fiji
    0.47
     colorWith
    0.46
    
    0.46
     P
    0.45
     
    0.45
     dzī
    0.45
    Activations Density 0.050%

    No Known Activations