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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 7396
    Prev
    Next
    INDEX
    Explanations

    numerical statistics or performance metrics in sports contexts

    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
    ########.
    -0.94
    +#+#
    -0.93
    rungsseite
    -0.86
     queſta
    -0.85
     AssemblyCulture
    -0.82
    Personendaten
    -0.81
     المعيارى
    -0.79
     informée
    -0.79
     Infórmanos
    -0.77
     يتيمه
    -0.75
    POSITIVE LOGITS
     last
    0.32
     Monday
    0.31
    
    0.30
     yesterday
    0.28
    O
    0.27
    T
    0.27
    null
    0.27
     evening
    0.26
     r
    0.26
     Tuesday
    0.26
    Activations Density 0.003%

    No Known Activations