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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15-GEMMASCOPE-RES-16K
    6. 12926
    Prev
    Next
    INDEX
    Explanations

    terms associated with depth and intensity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    antMatchers
    -0.85
    urlpatterns
    -0.82
    MessageTagHelper
    -0.79
    RegistryLite
    -0.78
    ModelAdmin
    -0.78
     propOrder
    -0.77
    ViewFeatures
    -0.77
     ModelRenderer
    -0.76
    RenderAtEndOf
    -0.76
    queryInterface
    -0.76
    POSITIVE LOGITS
     DEEP
    1.55
     deep
    1.50
     depths
    1.50
     depth
    1.48
     Deep
    1.43
     DEPTH
    1.41
     Depth
    1.36
    DEEP
    1.36
    Deep
    1.33
    deep
    1.28
    Activations Density 0.078%

    No Known Activations