© 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. 1-GEMMASCOPE-RES-16K
    11. 7645
    Prev
    Next
    INDEX
    Explanations

    informal second-person pronouns and expressions indicative of casual conversation

    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
    •Temporal SAE vs GemmaScope Comparison

    No Comments

    Negative Logits
     "<?
    -0.50
    writeValue
    -0.49
     "
    -0.49
    skem
    -0.49
    ImageIO
    -0.48
    potamus
    -0.48
     objectForKey
    -0.47
    Външни
    -0.47
    請繼續往下閱讀
    -0.46
    конец
    -0.45
    POSITIVE LOGITS
     ppl
    1.05
     صوتيه
    1.02
     feroit
    1.00
     pouvoit
    0.97
     outta
    0.96
     prolly
    0.93
     auroit
    0.93
     lemme
    0.92
     yall
    0.91
     thyself
    0.90
    Activations Density 0.210%

    No Known Activations