© 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. 2-GEMMASCOPE-RES-16K
    11. 13869
    Prev
    Next
    INDEX
    Explanations

    repeated mentions of the word "matter."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Filmografia
    -0.52
     secure
    -0.37
     consultato
    -0.36
     whether
    -0.36
    ˏ
    -0.35
    נע
    -0.35
    secure
    -0.35
     выбо
    -0.34
     nouve
    -0.32
    estris
    -0.32
    POSITIVE LOGITS
     matter
    1.02
    matter
    0.92
     framework
    0.86
     MATTER
    0.85
    framework
    0.79
     FRAMEWORK
    0.78
     Matter
    0.76
     frameworks
    0.76
     Framework
    0.75
    Matter
    0.75
    Activations Density 0.093%

    No Known Activations