© 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 - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 28385
    Prev
    Next
    INDEX
    Explanations

    the beginning of structured documents, such as patents or formal applications

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

    compose and send emails

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    :✨
    -0.84
    الإنجليزية
    -0.79
    RegistryLite
    -0.74
     StatefulWidget
    -0.73
     BrowserModule
    -0.73
     ويكيميديا
    -0.71
     autorytatywna
    -0.70
     MonoBehaviour
    -0.69
    rungsseite
    -0.64
     UnityEngine
    -0.63
    POSITIVE LOGITS
     mail
    0.92
    Mail
    0.84
    mail
    0.81
    smtp
    0.80
     Mail
    0.80
     email
    0.75
     Gmail
    0.75
     SMTP
    0.75
     MAIL
    0.75
    MAIL
    0.71
    Activations Density 0.240%

    No Known Activations