© 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. 56320
    Prev
    Next
    INDEX
    Explanations

    mentions of resources and their allocation in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     jamás
    -0.37
     ModelExpression
    -0.36
     actionPerformed
    -0.36
     Privacidade
    -0.36
    afterEach
    -0.35
     arrep
    -0.35
     dokun
    -0.34
     hoş
    -0.34
    AdapterView
    -0.33
     appunto
    -0.33
    POSITIVE LOGITS
     resources
    1.25
     Resources
    1.09
     RESOURCES
    1.01
    resources
    1.01
    Resources
    1.00
    資源
    0.97
     recursos
    0.95
    RESOURCES
    0.94
     ressources
    0.93
     risorse
    0.91
    Activations Density 0.035%

    No Known Activations