© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 13791
    Prev
    Next
    INDEX
    Explanations

    indications of impending events or crises

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     amizade
    -0.54
     mitad
    -0.48
     paisagem
    -0.46
     ragione
    -0.46
     visão
    -0.45
     consciência
    -0.45
     mostrarse
    -0.45
    wpi
    -0.44
     ligação
    -0.44
     boneca
    -0.44
    POSITIVE LOGITS
     impending
    1.00
    upcoming
    0.94
     imminent
    0.93
     upcoming
    0.90
     Upcoming
    0.80
    Upcoming
    0.78
    即将
    0.77
     forthcoming
    0.76
     approaching
    0.69
     awaiting
    0.69
    Activations Density 0.150%

    No Known Activations