© 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-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 12079
    Prev
    Next
    INDEX
    Explanations

    references to construction or improvement processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 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
     propOrder
    -0.69
    complexContent
    -0.64
    SerializedName
    -0.57
    Weblinks
    -0.56
     ostavi
    -0.54
     beginnetje
    -0.53
     AssemblyTitle
    -0.52
     سكانية
    -0.51
    égorie
    -0.51
     समीक्षाओं
    -0.50
    POSITIVE LOGITS
     happen
    1.03
     appear
    0.93
     seem
    0.91
     look
    0.89
     feel
    0.85
    happen
    0.78
    appear
    0.74
     palatable
    0.73
     possible
    0.72
     accessible
    0.71
    Activations Density 0.258%

    No Known Activations