© 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. 7584
    Prev
    Next
    INDEX
    Explanations

    terms related to media types and media concepts

    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
     plegable
    -0.37
     competición
    -0.33
     doctrina
    -0.32
     votación
    -0.32
    jukan
    -0.32
     compéti
    -0.31
    ถม
    -0.31
     inyección
    -0.31
     agrav
    -0.31
    YourGuide
    -0.30
    POSITIVE LOGITS
     media
    3.91
     Media
    3.78
    Media
    3.75
    media
    3.69
     MEDIA
    3.48
    MEDIA
    3.25
     Medien
    2.78
    媒体
    2.58
     medias
    2.56
    メディア
    2.55
    Activations Density 0.146%

    No Known Activations