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. 3-GEMMASCOPE-RES-16K
    6. 8027
    Prev
    Next
    INDEX
    Explanations

    sections of legal documents, focusing on references to appeals, petitions, and court rulings

    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
    AndEndTag
    -0.98
    SharedDtor
    -0.76
    anskje
    -0.72
    /$',
    -0.63
    AsUp
    -0.62
    septic
    -0.62
    GeneratedValue
    -0.61
    źródło
    -0.61
     Outdoor
    -0.60
    complexType
    -0.60
    POSITIVE LOGITS
      
    0.55
    bbene
    0.53
    snackbar
    0.49
    さて
    0.48
     douleurs
    0.47
     Хотя
    0.47
     talle
    0.47
     sfera
    0.46
     chrétiens
    0.46
     merke
    0.46
    Activations Density 0.399%

    No Known Activations