© 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. 5-GEMMASCOPE-RES-16K
    11. 6817
    Prev
    Next
    INDEX
    Explanations

    references to specific locations and cultural contexts related to terrorism and social issues in South Asia

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

    mentions of specific locations, particularly in South Asia

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegistryLite
    -0.65
    insee
    -0.56
    titleMargin
    -0.53
     cuchar
    -0.51
     Hence
    -0.50
    timis
    -0.50
     CallOverrides
    -0.49
     specchio
    -0.49
    DockStyle
    -0.49
    queryInterface
    -0.49
    POSITIVE LOGITS
     Pakistan
    1.14
     Pakistani
    1.11
    Pakistan
    1.08
     pakistan
    0.92
    riwal
    0.82
    istani
    0.81
     Punjab
    0.81
     urdu
    0.80
     Lahore
    0.79
     Urdu
    0.78
    Activations Density 0.507%

    No Known Activations