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. 11-GEMMASCOPE-RES-16K
    6. 5857
    Prev
    Next
    INDEX
    Explanations

    temporal references and indications of time frames

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )";
    
    -0.91
    ".
    
    -0.84
    )");
    
    -0.84
    bootstrapcdn
    -0.78
    )":
    -0.77
     ")
    
    -0.77
    AddTagHelper
    -0.75
     Paglinawan
    -0.75
     EnglishChoose
    -0.74
    Hentet
    -0.74
    POSITIVE LOGITS
    .
    0.55
    Linq
    0.55
    ,
    0.54
    нее
    0.50
    Pfalz
    0.50
    jws
    0.48
     nhất
    0.47
     dazu
    0.47
    AMENTE
    0.46
     tour
    0.46
    Activations Density 0.377%

    No Known Activations