© 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. 25-GEMMASCOPE-RES-16K
    11. 15717
    Prev
    Next
    INDEX
    Explanations

    references to the destruction or preservation of physical objects and their significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     concentration
    -0.46
     coherence
    -0.40
    scriptcase
    -0.36
     activities
    -0.36
     dynamics
    -0.34
     culture
    -0.34
     cohesion
    -0.33
    OrderInfo
    -0.33
    RefNanny
    -0.33
     main
    -0.33
    POSITIVE LOGITS
     belonged
    0.57
    RenderAtEndOf
    0.56
    Derbyniad
    0.54
    StoryboardSegue
    0.54
    belong
    0.52
     belongs
    0.51
    Vorlage
    0.50
     uſed
    0.50
     pemberian
    0.49
     trône
    0.49
    Activations Density 0.600%

    No Known Activations