© 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. 41958
    Prev
    Next
    INDEX
    Explanations

    references to construction or development projects

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

    project

    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
    XmlAccessType
    -0.39
     étanche
    -0.38
    mbox
    -0.38
     habitudes
    -0.37
     kebiasaan
    -0.35
     semanal
    -0.35
     colors
    -0.34
     arkadaş
    -0.34
    indépendance
    -0.33
     bronce
    -0.33
    POSITIVE LOGITS
     Project
    0.79
    IntoConstraints
    0.78
     project
    0.77
     projectId
    0.76
     Projekt
    0.71
     proyecto
    0.69
    projectId
    0.68
     Projects
    0.66
     projeto
    0.66
     projektu
    0.64
    Activations Density 0.007%

    No Known Activations