© 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. 3-GEMMASCOPE-RES-16K
    11. 10001
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Microsoft"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     plot
    -0.40
     corner
    -0.39
     pureza
    -0.38
     deposition
    -0.35
     deposit
    -0.35
     plots
    -0.35
     deposited
    -0.35
     الرياضيه
    -0.35
    wertig
    -0.35
     dump
    -0.34
    POSITIVE LOGITS
     Microsoft
    2.70
    Microsoft
    2.66
     microsoft
    2.03
    microsoft
    1.85
    微软
    1.45
     Google
    1.37
    Google
    1.27
     Xbox
    1.13
     Windows
    1.12
     google
    1.03
    Activations Density 0.051%

    No Known Activations