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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 20-GEMMASCOPE-RES-16K
    6. 15634
    Prev
    Next
    INDEX
    Explanations

    HTML elements and attributes indicative of user interfaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    HTML attributes starting with =" or style properties

    np_acts-logits-general · gemini-2.0-flash

    HTML and CSS styling attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewImports
    -0.64
    ResponseWriter
    -0.62
    Javadoc
    -0.54
    RTLD
    -0.53
     privées
    -0.50
    urlpatterns
    -0.50
    EndInit
    -0.50
     ProtoMessage
    -0.49
    IUrlHelper
    -0.48
    httphttps
    -0.47
    POSITIVE LOGITS
    ynb
    0.61
    Diweddarwch
    0.51
     Giri
    0.51
     cathedral
    0.50
     ktorí
    0.50
    ListTile
    0.49
     doble
    0.48
     mb
    0.48
    יוחד
    0.48
    pertoire
    0.47
    Activations Density 0.072%

    No Known Activations