© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 16941
    Prev
    Next
    INDEX
    Explanations

    references to software development or programming elements

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

    UI elements and authors

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     köp
    -0.33
    setBounds
    -0.31
     celebrado
    -0.31
     habilidad
    -0.30
     Gobernador
    -0.29
     Umum
    -0.28
     Sociales
    -0.27
    BuildContext
    -0.27
    خواندن
    -0.26
    affaire
    -0.26
    POSITIVE LOGITS
    logo
    1.13
     logo
    0.99
    Personensuche
    0.98
    titleMargin
    0.97
    Logo
    0.95
     Logo
    0.94
     arşivlendi
    0.91
    reportWebVitals
    0.90
     LOGO
    0.88
     AssemblyTitle
    0.87
    Activations Density 0.000%

    No Known Activations