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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 9111
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing specific quantities or descriptors

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

    Followed by "quick" or "brief"

    np_acts-logits-general · gemini-2.0-flash

    a quick note or disclosure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lamic
    -0.57
    Geplaatst
    -0.54
     ấy
    -0.54
    bilirsiniz
    -0.48
    yaç
    -0.48
    ză
    -0.47
     nélk
    -0.46
     τὴν
    -0.45
     portrayed
    -0.45
     éxitos
    -0.45
    POSITIVE LOGITS
     quick
    1.29
    quick
    1.02
     QUICK
    0.97
     brief
    0.90
     little
    0.89
     Quick
    0.88
    QUICK
    0.84
    Quick
    0.83
     snabb
    0.80
     caveat
    0.78
    Activations Density 0.269%

    No Known Activations