Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 9292
    Prev
    Next
    INDEX
    Explanations

    phrases related to socio-economic disparities and welfare

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AccessorTable
    -0.58
    #![
    -0.57
    ArgumentParser
    -0.50
    featureID
    -0.50
    RegistryLite
    -0.50
     HasFactory
    -0.47
    saraba
    -0.46
    原始内容存档于
    -0.46
     ***!
    -0.45
    SourceChecksum
    -0.44
    POSITIVE LOGITS
     dead
    0.76
     wealthy
    0.71
     rich
    0.70
     fittest
    0.70
     weak
    0.69
     faint
    0.66
     needy
    0.65
     elderly
    0.62
     meek
    0.62
     masses
    0.62
    Activations Density 0.127%

    No Known Activations