© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 56142
    Prev
    Next
    INDEX
    Explanations

    instances of the word "seize" and its variations

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

    seize or seizure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    tanleria
    -0.62
     المعيارى
    -0.59
    DateTimeFormat
    -0.54
    Parcelize
    -0.52
    lamabad
    -0.50
     Waterman
    -0.50
     ExecuteAsync
    -0.49
    inputType
    -0.48
    ARROLL
    -0.48
    ttt
    -0.48
    POSITIVE LOGITS
     seizure
    0.90
     Seiz
    0.86
     seize
    0.77
     seizing
    0.70
     seized
    0.69
     seizures
    0.65
     seiz
    0.65
     Seizures
    0.60
     Siege
    0.51
    Levi
    0.50
    Activations Density 0.005%

    No Known Activations