© 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. 20-GEMMASCOPE-RES-16K
    11. 11253
    Prev
    Next
    INDEX
    Explanations

    instances of sudden and unexpected appearances or situations, often related to surveillance or observation

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

    "suddenly" or sudden events

    np_acts-logits-general · gemini-2.0-flash

    suddenly or unexpectedly appears/disappears

    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
    ishable
    -0.51
     fortsatt
    -0.48
     tetap
    -0.45
    safe
    -0.44
    ต่อไป
    -0.44
    fahr
    -0.43
     weiterhin
    -0.43
     blijven
    -0.42
    KeepAlive
    -0.42
    繼續
    -0.42
    POSITIVE LOGITS
     suddenly
    2.32
     sudden
    2.06
    suddenly
    2.06
     unexpectedly
    2.03
     Suddenly
    1.95
    Suddenly
    1.90
     soudain
    1.86
     plötzlich
    1.83
     unexpected
    1.80
    unexpected
    1.70
    Activations Density 0.401%

    No Known Activations