© 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. 14137
    Prev
    Next
    INDEX
    Explanations

    references to local government and news-related topics

    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
     akik
    -0.54
     who
    -0.47
     hendes
    -0.43
    duğu
    -0.41
     Who
    -0.40
    who
    -0.40
     umane
    -0.40
    vov
    -0.39
    gados
    -0.39
    女人的
    -0.37
    POSITIVE LOGITS
     spokeswoman
    1.32
     spokesman
    1.22
     Director
    1.17
     President
    1.17
     historian
    1.17
     Chief
    1.16
     officials
    1.12
     economist
    1.12
     Chairman
    1.11
     founder
    1.09
    Activations Density 0.200%

    No Known Activations