© 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
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 7400
    Prev
    Next
    INDEX
    Explanations

    phrases related to military action and geopolitical conflict

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

    Followed by certain nouns (war, regime, world)

    np_acts-logits-general · gemini-2.0-flash

    war, default, collapse, conflict

    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
     telah
    -0.41
     Lately
    -0.37
     journaux
    -0.36
     lately
    -0.35
     recientemente
    -0.35
     constantemente
    -0.33
    cellaneous
    -0.33
     đã
    -0.32
     recently
    -0.32
     sedang
    -0.32
    POSITIVE LOGITS
     betweenstory
    0.61
     drastic
    0.57
    webElementGuid
    0.56
     JpaRepository
    0.56
    migrationBuilder
    0.56
    dras
    0.55
    TagMode
    0.53
     scénario
    0.52
    transQ
    0.51
    بوابة
    0.51
    Activations Density 0.590%

    No Known Activations