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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-GEMMASCOPE-RES-16K
    6. 13173
    Prev
    Next
    INDEX
    Explanations

    concepts related to the impact of modern challenges on society and the importance of adapting to change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    нрави
    -0.57
    nodoc
    -0.52
     viens
    -0.52
     externa
    -0.52
     ElementRef
    -0.49
     compi
    -0.49
    ilarang
    -0.49
     IDisposable
    -0.49
     avoit
    -0.48
    strze
    -0.48
    POSITIVE LOGITS
     modern
    0.89
     modernisation
    0.82
     modernization
    0.81
    modern
    0.80
     moderni
    0.80
     moderne
    0.79
     modernity
    0.78
     contemporary
    0.78
     modernize
    0.76
     modernized
    0.73
    Activations Density 0.219%

    No Known Activations