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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9-GEMMASCOPE-RES-16K
    6. 15141
    Prev
    Next
    INDEX
    Explanations

    references to New York and its associated entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personensuche
    -0.95
     udf
    -0.88
    paravant
    -0.86
     JST
    -0.84
     Chengdu
    -0.82
     ujednoznacz
    -0.81
     NLA
    -0.80
     PropTypes
    -0.78
    ']
    
    -0.77
     Kodi
    -0.77
    POSITIVE LOGITS
     York
    1.66
     YORK
    1.45
    York
    1.36
    YORK
    1.22
     york
    1.14
     NY
    1.12
    york
    0.98
     Yorkers
    0.95
    орк
    0.93
     Yorke
    0.85
    Activations Density 0.045%

    No Known Activations