Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 16-GEMMASCOPE-RES-16K
    6. 16012
    Prev
    Next
    INDEX
    Explanations

    references to legal proceedings and the emotions tied to familial connections

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

    Communicating or reaching out to someone

    np_acts-logits-general · gemini-2.0-flash

    sending mail or messages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ujednoznacz
    -0.67
     autorytatywna
    -0.57
    AccessorTable
    -0.56
    fhir
    -0.55
    tagHelperRunner
    -0.54
     cherchés
    -0.54
     Bühne
    -0.53
     الحره
    -0.53
     Energía
    -0.49
     kaarangay
    -0.49
    POSITIVE LOGITS
     sending
    0.86
     Sending
    0.81
    Sending
    0.78
    sending
    0.78
     send
    0.76
     sends
    0.75
     sent
    0.70
    思念
    0.70
    send
    0.69
     Send
    0.69
    Activations Density 0.250%

    No Known Activations