© 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. 3-GEMMASCOPE-RES-16K
    11. 230
    Prev
    Next
    INDEX
    Explanations

    expressions of personal reflection or consideration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kloped
    -0.81
    Mek
    -0.76
     Mek
    -0.73
    ing
    -0.70
    muk
    -0.66
    elsen
    -0.63
    xically
    -0.63
    k
    -0.62
     yere
    -0.60
    
    -0.59
    POSITIVE LOGITS
     thought
    2.71
     Thought
    2.61
    Thought
    2.59
    thought
    2.55
     THOUGHT
    2.39
    thoughts
    1.14
     believed
    1.09
     dacht
    1.06
     thoughts
    1.01
     pensiero
    1.01
    Activations Density 0.061%

    No Known Activations