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. 13-GEMMASCOPE-RES-16K
    6. 10041
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to computing, particularly regarding resource management and limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ó
    -0.49
    tokio
    -0.46
    ouvoir
    -0.45
     NSMutable
    -0.45
     Zaj
    -0.45
    GEST
    -0.45
    NSObject
    -0.44
    μιουργ
    -0.43
    eake
    -0.43
    kopp
    -0.43
    POSITIVE LOGITS
    ↵
    1.88
     […]
    1.27
    ↵↵
    1.20
    ',...
    1.18
     =
    
    1.07
    ...')
    1.01
    </h3>
    1.00
    ,...
    0.98
    IntoConstraints
    0.97
    )=$
    0.96
    Activations Density 5.921%

    No Known Activations