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-2-9B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 7156
    Prev
    Next
    INDEX
    Explanations

    references to email and email-related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     planten
    -0.44
     soorten
    -0.44
     herói
    -0.41
     natuur
    -0.40
     fatores
    -0.39
     ListNode
    -0.39
    таратура
    -0.39
     circonstances
    -0.38
    alanta
    -0.38
     punte
    -0.38
    POSITIVE LOGITS
     email
    1.54
     Email
    1.40
    Email
    1.39
     emails
    1.30
    email
    1.26
     EMAIL
    1.24
     emailing
    1.23
    Emails
    1.16
    getEmail
    1.16
     emailed
    1.15
    Activations Density 0.102%

    No Known Activations