© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 11410
    Prev
    Next
    INDEX
    Explanations

    references to indoor recreational activities and spaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
     paisagem
    -0.34
    rigin
    -0.34
    chaqueta
    -0.34
     Haziran
    -0.34
     Shanks
    -0.33
     населения
    -0.33
     Childhood
    -0.33
    遍
    -0.33
     uniwers
    -0.32
    arget
    -0.32
    POSITIVE LOGITS
     indoor
    1.08
     indoors
    1.03
    Indoor
    0.96
     Indoor
    0.94
    indoor
    0.92
     interior
    0.86
    Interior
    0.82
    室内
    0.78
     intérieur
    0.77
    Inside
    0.76
    Activations Density 0.172%

    No Known Activations