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

    Neuronpedia

    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. 5502
    Prev
    Next
    INDEX
    Explanations

    specific terms related to social and economic issues

    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
    s
    -1.23
    ים
    -0.94
     disponibilités
    -0.90
     armado
    -0.87
    jména
    -0.87
    ValueStyle
    -0.87
    Kaynakça
    -0.81
    es
    -0.81
     Bhatt
    -0.81
    bisoft
    -0.80
    POSITIVE LOGITS
     initState
    0.66
    Rö
    0.65
     Eis
    0.65
     Kel
    0.64
     lila
    0.64
    хни
    0.63
     Khi
    0.63
    ation
    0.63
    ัจ
    0.63
     Pome
    0.63
    Activations Density 0.896%

    No Known Activations