© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 39-GEMMASCOPE-RES-16K
    6. 3969
    Prev
    Next
    INDEX
    Explanations

    terms related to communication and correspondence, especially within a legal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -0.60
    存于互联网档案馆
    -0.58
     disponibilités
    -0.51
     שוליים
    -0.50
    saraba
    -0.49
     disambiguazione
    -0.49
    queryInterface
    -0.48
     EconPapers
    -0.47
    Bronnen
    -0.45
    AISSEE
    -0.45
    POSITIVE LOGITS
     requests
    1.08
     calls
    0.91
     messages
    0.87
     incoming
    0.82
     queries
    0.79
    requests
    0.77
     emails
    0.75
     inquiries
    0.75
     inqu
    0.63
     Requests
    0.63
    Activations Density 0.753%

    No Known Activations