© 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. 15815
    Prev
    Next
    INDEX
    Explanations

    references to political organizations and individuals involved in activism or reform movements

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

    Preceding certain nouns

    np_acts-logits-general · gemini-2.0-flash

    without

    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
     myſelf
    -1.00
     purpoſe
    -0.95
     pleaſure
    -0.94
     ſeveral
    -0.90
     betweenstory
    -0.86
     theſe
    -0.83
     leaſt
    -0.83
     reaſon
    -0.81
     vectorstock
    -0.79
     Efq
    -0.79
    POSITIVE LOGITS
     without
    1.13
    without
    0.96
     meets
    0.95
     Without
    0.94
    Without
    0.91
     WITHOUT
    0.87
     zonder
    0.82
     tanpa
    0.81
    WITHOUT
    0.79
     at
    0.78
    Activations Density 0.379%

    No Known Activations