© 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. 20-GEMMASCOPE-RES-16K
    11. 4403
    Prev
    Next
    INDEX
    Explanations

    instances of personal pronouns and assessments of individual experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Followed by "but" or "also"

    np_acts-logits-general · gemini-2.0-flash

    pronoun and followed by a contrasting conjunction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     therefore
    -0.95
     zwar
    -0.91
     sice
    -0.89
    therefore
    -0.85
     even
    -0.81
     hence
    -0.78
     infatti
    -0.78
    thus
    -0.77
    จึง
    -0.76
     thus
    -0.74
    POSITIVE LOGITS
     nonetheless
    1.14
     ändå
    1.13
     nevertheless
    1.12
    却
    1.10
    卻
    1.09
    却是
    1.05
     lại
    1.01
     digress
    0.99
    却被
    0.97
     trotzdem
    0.95
    Activations Density 0.667%

    No Known Activations