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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 18920
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to protective measures or barriers against various threats

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

    environmental hazards and dangers

    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
    delwed
    -0.67
    rungsseite
    -0.57
     للمعارف
    -0.55
    chemise
    -0.53
     initComponents
    -0.52
     الحره
    -0.52
    heitsbild
    -0.51
    StoryboardSegue
    -0.50
    icano
    -0.49
    脚注の使い方
    -0.49
    POSITIVE LOGITS
     diseases
    0.43
     quelconque
    0.40
     viruses
    0.37
     dangers
    0.36
     hazards
    0.35
     quelcon
    0.34
     temptations
    0.34
     illnesses
    0.34
     barriers
    0.33
    來自
    0.33
    Activations Density 0.019%

    No Known Activations