© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 10318
    Prev
    Next
    INDEX
    Explanations

    concepts related to political and social dynamics

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

    a crisis or turning point

    np_acts-logits-general · gemini-2.0-flash

    dire circumstances and crises

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     standardize
    -0.51
     chi̍t
    -0.46
     pemberian
    -0.46
     wydaj
    -0.45
    AsUp
    -0.45
    solicited
    -0.43
     yeşil
    -0.42
     niebies
    -0.42
     Standardi
    -0.42
     standaard
    -0.41
    POSITIVE LOGITS
     unprecedented
    0.67
     '\\;'
    0.65
     crisis
    0.57
     crises
    0.57
     epoch
    0.54
     global
    0.54
     political
    0.52
     crise
    0.51
    Estamos
    0.49
     witnessed
    0.48
    Activations Density 0.514%

    No Known Activations