© 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. 23-GEMMASCOPE-RES-16K
    11. 7121
    Prev
    Next
    INDEX
    Explanations

    references to collective actions and sentiments in a community context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     conmigo
    -1.12
     comigo
    -1.05
     me
    -0.97
     Itself
    -0.94
     dirinya
    -0.87
    私に
    -0.83
     asegurarse
    -0.83
     itself
    -0.81
    itself
    -0.80
     magát
    -0.79
    POSITIVE LOGITS
     ourselves
    2.29
     our
    1.19
     можем
    1.08
     знаем
    1.08
    our
    0.97
     видим
    0.96
     будем
    0.91
    Our
    0.90
     Our
    0.85
     داریم
    0.85
    Activations Density 0.700%

    No Known Activations