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 - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 5744
    Prev
    Next
    INDEX
    Explanations

    references to the IEEE and the concept of convenience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    guenos
    -0.84
     uParam
    -0.83
    WebVitals
    -0.81
     prévoit
    -0.81
     sqlalchemy
    -0.78
    ală
    -0.77
     Rojas
    -0.76
     bVar
    -0.75
    Weblinks
    -0.73
     Eindhoven
    -0.72
    POSITIVE LOGITS
     Jeanette
    0.90
    Datuak
    0.78
     createState
    0.77
    האם
    0.73
    visiae
    0.72
    írus
    0.68
     healthcare
    0.68
     convention
    0.67
     Abbott
    0.67
     Audrey
    0.66
    Activations Density 0.081%

    No Known Activations