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-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 16272
    Prev
    Next
    INDEX
    Explanations

    expressions of personal thoughts and feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Covid
    -0.98
    . 
    -0.96
    Covid
    -0.86
    https
    -0.85
     covid
    -0.85
     https
    -0.81
    ️
    -0.80
     pandemia
    -0.79
     
    -0.79
     TikTok
    -0.78
    POSITIVE LOGITS
    faßt
    0.87
     definately
    0.80
     ^_^
    0.80
     Daß
    0.79
     idéia
    0.79
     =)
    0.78
     muß
    0.71
     Miß
    0.70
     mußten
    0.70
     hehe
    0.66
    Activations Density 2.563%

    No Known Activations