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. 1-GEMMASCOPE-RES-16K
    6. 7867
    Prev
    Next
    INDEX
    Explanations

    references to China and its related entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Foire
    -0.63
    ysacchar
    -0.62
     Lombar
    -0.61
    ToBounds
    -0.60
     colombiana
    -0.60
     colombiano
    -0.59
    TPS
    -0.59
     Semp
    -0.58
    ConstraintMaker
    -0.57
     poffe
    -0.57
    POSITIVE LOGITS
     China
    3.78
    China
    3.38
     CHINA
    3.09
     china
    2.96
     Chinese
    2.71
    CHINA
    2.57
    china
    2.52
    Chinese
    2.31
     Chine
    2.24
     Китай
    2.16
    Activations Density 0.052%

    No Known Activations