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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 11627
    Prev
    Next
    INDEX
    Explanations

    references to organizational structure and operational details of companies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jsonwebtoken
    -0.84
     propOrder
    -0.81
     AssemblyProduct
    -0.80
     CreateTagHelper
    -0.79
    IVEREF
    -0.77
     kaarangay
    -0.76
     يتيمه
    -0.74
     wireType
    -0.72
     bezeichneter
    -0.67
     StringTokenizer
    -0.66
    POSITIVE LOGITS
     headquarters
    1.21
     Headquarters
    1.00
     location
    0.95
     locations
    0.94
     offices
    0.90
    Headquarters
    0.89
     HQ
    0.88
     office
    0.85
     siedz
    0.83
     sede
    0.79
    Activations Density 0.210%

    No Known Activations