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. 6612
    Prev
    Next
    INDEX
    Explanations

    references to corporate deals or agreements

    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
     OnInit
    -0.50
    ="./
    -0.48
    featureID
    -0.47
     {}));
    -0.47
    ))[
    -0.43
    AnimationsModule
    -0.42
    Externe
    -0.42
     %
    -0.41
    Обра
    -0.41
     Commencez
    -0.41
    POSITIVE LOGITS
     Monfieur
    0.89
     purpoſe
    0.88
     Majefty
    0.87
    By
    0.86
     themſelves
    0.85
     Jefus
    0.83
     houſe
    0.82
    WASHINGTON
    0.81
    Autoritní
    0.81
     ſeveral
    0.80
    Activations Density 0.104%

    No Known Activations