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. 21-GEMMASCOPE-RES-16K
    6. 2776
    Prev
    Next
    INDEX
    Explanations

    code snippets related to email handling and authentication processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegistryLite
    -0.82
     مرئيه
    -0.79
    ंदीखरीदारी
    -0.68
     kasarigan
    -0.58
    Попис
    -0.58
     onCreateView
    -0.58
    mybatisplus
    -0.57
     UnityEngine
    -0.55
    amiento
    -0.55
    Controllo
    -0.55
    POSITIVE LOGITS
     sender
    1.23
     Mail
    1.14
     mail
    1.12
     MAIL
    1.06
     sending
    1.06
     send
    1.05
    smtp
    1.05
     SMTP
    1.03
     Sender
    1.03
     recipients
    1.01
    Activations Density 0.316%

    No Known Activations