© 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
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 9865
    Prev
    Next
    INDEX
    Explanations

    references to covert operations or interventions

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

    Military or political strategies

    np_acts-logits-general · gemini-2.0-flash

    strategies and tactics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IBOutlet
    -0.61
    MessageTagHelper
    -0.54
     ujednoznacz
    -0.52
    WithIOException
    -0.50
     cdti
    -0.49
    ="@+
    -0.48
     arşivlendi
    -0.47
    RectangleBorder
    -0.47
    OrNil
    -0.47
    jsxFileName
    -0.45
    POSITIVE LOGITS
     tactics
    1.83
     strategy
    1.79
     tactic
    1.70
     strategies
    1.70
    strategy
    1.52
     stratégie
    1.47
     estrategia
    1.43
    strategies
    1.41
     Strategy
    1.37
     tricks
    1.37
    Activations Density 0.773%

    No Known Activations