© 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
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104713
    Prev
    Next
    INDEX
    Explanations

    section headers and other structural elements in documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    createCell
    -0.49
    andExpect
    -0.49
    الإنجليزية
    -0.45
     PROF
    -0.44
    pendicular
    -0.43
    疎
    -0.43
     uts
    -0.42
     Ful
    -0.42
     frow
    -0.41
     FUT
    -0.41
    POSITIVE LOGITS
     Lingkungan
    0.61
     aislado
    0.57
    
    0.55
     automatiques
    0.54
     aislada
    0.54
     vacía
    0.54
     isolado
    0.53
     indipendente
    0.52
    ⓘ
    0.52
     desierto
    0.51
    Activations Density 0.003%

    No Known Activations