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 - 65k
    5. 17-GEMMASCOPE-RES-65K
    6. 28387
    Prev
    Next
    INDEX
    Explanations

    information related to sports statistics, particularly player performance and injury details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_65k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     contextLoads
    -0.95
     Мексичка
    -0.91
    SharedDtor
    -0.82
    enumi
    -0.81
    
    -0.80
     MainAxisSize
    -0.80
     Efq
    -0.77
    oredCriteria
    -0.76
    setVerticalGroup
    -0.76
     Jefus
    -0.74
    POSITIVE LOGITS
     ...
    0.98
    ...
    0.94
     ....
    0.83
     ..
    0.82
    ....
    0.82
    .....
    0.81
    ……
    0.81
     …
    0.80
    …
    0.80
    ….
    0.77
    Activations Density 0.522%

    No Known Activations