© 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. 21-GEMMASCOPE-RES-16K
    11. 12249
    Prev
    Next
    INDEX
    Explanations

    references to authoritarian government structures and political repression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BrowserModule
    -0.62
    Elemental
    -0.55
     Brabant
    -0.52
    \{\\
    -0.52
    サリー
    -0.51
    Pautan
    -0.51
    prefixer
    -0.51
    λλην
    -0.50
    complexType
    -0.49
     Elemental
    -0.49
    POSITIVE LOGITS
     Soviet
    1.19
     Communist
    1.02
    Soviet
    1.02
     communist
    0.99
     Soviets
    0.99
     soviet
    0.93
     Stalin
    0.93
     USSR
    0.92
     communism
    0.87
     Communism
    0.85
    Activations Density 0.229%

    No Known Activations