© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 10823
    Prev
    Next
    INDEX
    Explanations

    references to specific e-reader devices and related technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Мексичка
    -0.88
     createSprite
    -0.85
     betweenstory
    -0.83
    TagHelper
    -0.82
     ModelExpression
    -0.79
     AssemblyTitle
    -0.78
    unknownFields
    -0.78
    ="@+
    -0.77
    GeneratedCode
    -0.75
    djangoproject
    -0.75
    POSITIVE LOGITS
     streaming
    0.74
     Spotify
    0.65
     Streaming
    0.60
     Netflix
    0.58
    Spotify
    0.55
    streaming
    0.55
     stream
    0.53
    oplayer
    0.53
     ebook
    0.52
    Streaming
    0.51
    Activations Density 0.306%

    No Known Activations