© 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. 16085
    Prev
    Next
    INDEX
    Explanations

    phrases related to balance and interconnection in various contexts

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

    followed by "while"

    np_acts-logits-general · gemini-2.0-flash

    achieving outcomes while

    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
    żd
    -0.64
    felf
    -0.58
    پیوند
    -0.57
    vábbi
    -0.56
    ailleurs
    -0.55
     تضيفلها
    -0.54
     ""],
    -0.54
    ofday
    -0.54
    >`;
    -0.53
    ungeon
    -0.52
    POSITIVE LOGITS
     without
    2.19
    without
    1.96
     Without
    1.77
    Without
    1.72
     WITHOUT
    1.69
     while
    1.66
     zonder
    1.60
    WITHOUT
    1.60
     ohne
    1.53
     tanpa
    1.51
    Activations Density 0.620%

    No Known Activations