© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 4263
    Prev
    Next
    INDEX
    Explanations

    key elements related to events and their details, especially in a structured context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preceding "event", "character", "residence", "city"

    np_acts-logits-general · gemini-2.0-flash

    main, primary, or capital concept

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LabelTagHelper
    -0.59
    RefNanny
    -0.57
    UObject
    -0.49
     HasFactory
    -0.48
    XMLHttpRequest
    -0.46
     plástica
    -0.44
    Transkript
    -0.43
    Jeografia
    -0.43
    pygame
    -0.43
    ufe
    -0.42
    POSITIVE LOGITS
    DockStyle
    0.54
     primary
    0.52
     utama
    0.48
    tispiece
    0.47
     huvud
    0.46
    WriteBarrier
    0.44
    Глав
    0.44
    Primary
    0.43
     principal
    0.43
     main
    0.43
    Activations Density 0.493%

    No Known Activations