© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 8604
    Prev
    Next
    INDEX
    Explanations

    the presence of the verb "to be" in various forms

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

    Preceding the word "are"

    np_acts-logits-general · gemini-2.0-flash

    being part of a description

    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
     a
    -0.59
     lèvres
    -0.58
     seseorang
    -0.57
     someone
    -0.55
     iemand
    -0.51
    Someone
    -0.51
     one
    -0.50
    ers
    -0.49
     domés
    -0.49
    las
    -0.49
    POSITIVE LOGITS
    wolves
    1.12
     Theſe
    1.02
     ligiloj
    0.99
     those
    0.92
     yourselves
    0.91
    Personendaten
    0.90
    ſelves
    0.87
    )";
    0.86
     assholes
    0.86
     themſelves
    0.84
    Activations Density 0.501%

    No Known Activations