© 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-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 2067
    Prev
    Next
    INDEX
    Explanations

    various forms and contexts of email communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    email or mail

    np_acts-logits-general · gemini-2.0-flash

    email and its communications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    email
    -0.88
     email
    -0.86
    Email
    -0.77
     Email
    -0.76
     emails
    -0.71
     ✭✭
    -0.69
     EMAIL
    -0.67
    emails
    -0.65
    EMAIL
    -0.64
     emailed
    -0.63
    POSITIVE LOGITS
    chimp
    0.59
     address
    0.57
     addresses
    0.55
    ers
    0.52
     blast
    0.52
     blasts
    0.51
    ings
    0.51
    发表于
    0.50
    er
    0.49
     marketing
    0.49
    Activations Density 0.105%

    No Known Activations