© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 15412
    Prev
    Next
    INDEX
    Explanations

    questions and expressions of uncertainty

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

    Tokens after question marks or periods

    np_acts-logits-general · gemini-2.0-flash

    uncertainty and continuation

    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
    DockStyle
    -0.66
    enderror
    -0.65
    териалы
    -0.63
     snart
    -0.60
    ########.
    -0.59
     Commencez
    -0.57
    お楽しみに
    -0.55
    ppsala
    -0.54
    ⎨
    -0.54
    どうやって
    -0.54
    POSITIVE LOGITS
     Personally
    0.96
     perhaps
    0.94
     personally
    0.94
    Personally
    0.94
     maybe
    0.90
     Perhaps
    0.84
    perhaps
    0.83
     Maybe
    0.82
     Certainly
    0.82
    Perhaps
    0.82
    Activations Density 0.313%

    No Known Activations