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

    Neuronpedia

    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. 103121
    Prev
    Next
    INDEX
    Explanations

    references to disasters, particularly in a contextual or thematic sense

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

    disasters and negative events

    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
     FetchType
    -0.62
     femininas
    -0.50
     Schülerinnen
    -0.47
     îna
    -0.47
    Office
    -0.47
     rubrique
    -0.45
     Prieto
    -0.45
    wikk
    -0.45
     féminine
    -0.44
    blico
    -0.44
    POSITIVE LOGITS
     disaster
    1.33
     Disaster
    1.27
    disaster
    1.19
    Disaster
    1.16
     disasters
    1.02
     katastro
    0.86
     catastrophe
    0.84
     desastre
    0.79
     catastrophes
    0.69
     getResult
    0.67
    Activations Density 0.002%

    No Known Activations