© 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. 9154
    Prev
    Next
    INDEX
    Explanations

    instances of the word "introduce" and similar variations, indicating a focus on introducing concepts or ideas

    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
     pomoci
    -0.55
    RenderAtEndOf
    -0.50
    TagMode
    -0.50
     stoff
    -0.49
     torebka
    -0.48
     juges
    -0.48
    Claim
    -0.47
    XmlAccessorType
    -0.47
    Council
    -0.45
     pajak
    -0.45
    POSITIVE LOGITS
     during
    1.05
     introducing
    1.02
     introduce
    0.99
     DURING
    0.92
    during
    0.91
     introduction
    0.90
     introduces
    0.87
     introdu
    0.84
     Introduce
    0.82
     Introducing
    0.81
    Activations Density 0.215%

    No Known Activations