© 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 - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 8759
    Prev
    Next
    INDEX
    Explanations

    disastrous events and their impacts

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

    Natural disasters and their aftermath

    np_acts-logits-general · gemini-2.0-flash

    natural disasters and devastation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '\\;'
    -0.33
    といって
    -0.32
     silicona
    -0.30
    ked
    -0.30
     disfru
    -0.30
    tronics
    -0.30
    intios
    -0.29
     Genève
    -0.28
     posesión
    -0.28
    ppet
    -0.28
    POSITIVE LOGITS
     Earthquake
    0.78
     earthquake
    0.76
     Disaster
    0.73
     disaster
    0.71
    Disaster
    0.71
    disaster
    0.70
     terremoto
    0.70
    Earthquake
    0.70
    localctx
    0.69
    bootstrapcdn
    0.67
    Activations Density 0.226%

    No Known Activations