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. 6100
    Prev
    Next
    INDEX
    Explanations

    mentions of specific organizations or associations within the context of the media and entertainment industry

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

    the UK or Britain

    np_acts-logits-general · gemini-2.0-flash

    British and UK related places

    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
    BagConstraints
    -0.67
     Dubuque
    -0.63
     Haitian
    -0.61
    Honolulu
    -0.60
     Winona
    -0.58
    ThroughAttribute
    -0.58
     Honolulu
    -0.58
     Guam
    -0.58
     Aloha
    -0.56
    Haiti
    -0.56
    POSITIVE LOGITS
     British
    2.18
     UK
    2.11
     Britain
    2.11
     London
    2.02
    British
    1.96
     England
    1.96
    Britain
    1.90
    UK
    1.85
    London
    1.83
     Britons
    1.82
    Activations Density 1.161%

    No Known Activations