Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 7301
    Prev
    Next
    INDEX
    Explanations

    references to different types of clubs or gatherings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __":
    -0.87
    BeginInit
    -0.86
    ])):
    -0.81
     RoutedEventArgs
    -0.80
    EOL
    -0.79
    ]))
    
    -0.78
     vectorielle
    -0.76
     Reste
    -0.76
     législ
    -0.75
     незавершена
    -0.74
    POSITIVE LOGITS
     club
    2.54
     Club
    2.41
     CLUB
    2.30
    Club
    2.29
    club
    2.25
     clubs
    2.18
     Clubs
    2.13
    CLUB
    2.12
    clubs
    1.83
    Clubs
    1.76
    Activations Density 0.066%

    No Known Activations