© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6585
    Prev
    Next
    INDEX
    Explanations

    phrases related to wealth inequality and economic power dynamics

    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
     Réponses
    -0.63
    FunctionFlags
    -0.51
     rano
    -0.51
     FAP
    -0.50
    latego
    -0.49
     interag
    -0.49
     neutre
    -0.49
     spontaneity
    -0.48
     matri
    -0.45
    mycin
    -0.45
    POSITIVE LOGITS
    verwijspagina
    0.69
     profit
    0.67
    Izvori
    0.66
     luxurious
    0.65
     benefits
    0.63
     benefit
    0.63
     benefiting
    0.63
     profite
    0.61
     selfish
    0.61
     hưởng
    0.61
    Activations Density 0.320%

    No Known Activations