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. 5983
    Prev
    Next
    INDEX
    Explanations

    references to subscription services and their features

    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
     AssemblyTitle
    -0.87
     فريبيس
    -0.85
     ExecuteAsync
    -0.83
    httphttps
    -0.83
    GEBURTSDATUM
    -0.82
    تقاوى
    -0.81
     שוליים
    -0.77
    NameInMap
    -0.75
    TagHelper
    -0.69
    PyExc
    -0.67
    POSITIVE LOGITS
     subscription
    1.07
     subscriptions
    0.86
     membership
    0.80
     Subscription
    0.78
    subscription
    0.77
     premium
    0.73
     Membership
    0.69
    Subscription
    0.69
     memberships
    0.67
    subscriptions
    0.65
    Activations Density 0.193%

    No Known Activations