Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 8048
    Prev
    Next
    INDEX
    Explanations

    references to geographic locations, particularly in the context of research studies

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

    Ghana or Ghanaian-related topics

    np_acts-logits-general · gemini-2.0-flash

    Ghanaian research

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mith
    -0.56
     heparin
    -0.55
    катери
    -0.53
     Sanskrit
    -0.51
    CharSequence
    -0.49
     Lalu
    -0.48
     subsp
    -0.48
    ISSIPPI
    -0.48
    federal
    -0.47
     muck
    -0.47
    POSITIVE LOGITS
     Ghana
    1.36
    Ghana
    1.24
     Ghanaian
    1.18
     Ghanaians
    1.16
     Accra
    1.14
    ghana
    0.97
     Ghan
    0.93
     GH
    0.93
     Ashanti
    0.92
     Tema
    0.86
    Activations Density 0.041%

    No Known Activations