© 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. 14875
    Prev
    Next
    INDEX
    Explanations

    conversational markers or references to speech

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

    Tokens after a period

    np_acts-logits-general · gemini-2.0-flash

    overall/analysts

    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
    tvguidetime
    -0.74
    WebServlet
    -0.72
    someone
    -0.61
    ipedia
    -0.57
    anyone
    -0.57
    iania
    -0.57
    everyone
    -0.56
    somebody
    -0.56
    extAlignment
    -0.55
    inguém
    -0.54
    POSITIVE LOGITS
     overall
    1.00
    Overall
    0.98
     Overall
    0.94
    overall
    0.87
    Analysts
    0.85
    总体
    0.82
     analysts
    0.81
    OVERALL
    0.80
    Meanwhile
    0.77
     Analysts
    0.76
    Activations Density 0.143%

    No Known Activations