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. 28377
    Prev
    Next
    INDEX
    Explanations

    elements related to dates and numbers

    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
    inete
    -0.52
    bolistas
    -0.46
    Hentet
    -0.46
    IsNotEmpty
    -0.45
    請繼續往下閱讀
    -0.44
    Referanser
    -0.43
    aleta
    -0.43
     E
    -0.43
    мули
    -0.42
     person
    -0.42
    POSITIVE LOGITS
    webElementXpaths
    0.92
     finally
    0.84
    finally
    0.83
    Finally
    0.81
     Finalmente
    0.80
     Finally
    0.79
    Finalmente
    0.78
    gelopen
    0.77
     finalmente
    0.77
     Endlich
    0.76
    Activations Density 0.047%

    No Known Activations