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. 3-GEMMASCOPE-RES-16K
    6. 11988
    Prev
    Next
    INDEX
    Explanations

    a focus on specific food items or dishes with cultural significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -1.05
    fjspx
    -0.97
    IsContent
    -0.93
     NSCoder
    -0.85
    extAlignment
    -0.72
    MLLoader
    -0.71
     виправивши
    -0.71
    ImageContext
    -0.70
     BoxFit
    -0.69
    Autoritní
    -0.67
    POSITIVE LOGITS
     suficientes
    0.53
     ihop
    0.52
     sépar
    0.52
     negras
    0.51
    urlpatterns
    0.51
     durer
    0.51
     scelte
    0.51
     fermés
    0.49
     verster
    0.49
     réunis
    0.49
    Activations Density 0.439%

    No Known Activations