© 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. 15-GEMMASCOPE-RES-16K
    11. 2600
    Prev
    Next
    INDEX
    Explanations

    discussions surrounding political norms and democratic integrity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.58
    κτηρισ
    -0.55
    Leary
    -0.50
    up
    -0.49
     خلف
    -0.45
     presto
    -0.45
    tapkan
    -0.45
     disambiguazione
    -0.45
    Group
    -0.43
     conclusive
    -0.43
    POSITIVE LOGITS
     démocr
    0.94
     democracy
    0.91
     estekak
    0.88
     démocratie
    0.87
     democracies
    0.79
    democracy
    0.79
     democratic
    0.78
     democracia
    0.73
    Democracy
    0.71
    Autoritní
    0.67
    Activations Density 0.401%

    No Known Activations