Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 13394
    Prev
    Next
    INDEX
    Explanations

    references to programming constructs and data handling within a coding context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebVitals
    -0.66
    "))
    
    -0.61
    ()");
    -0.58
    ()))
    
    -0.57
    FormTagHelper
    -0.57
    "]();
    -0.56
     AssemblyCulture
    -0.56
    ")))
    -0.56
     Galile
    -0.55
     transfieras
    -0.55
    POSITIVE LOGITS
    SQLiteDatabase
    0.65
    Skocz
    0.60
    eaways
    0.57
    onViewCreated
    0.57
    adpleegd
    0.56
     calculées
    0.56
    सन्दर्भ
    0.55
     &___
    0.55
    TimeUnit
    0.54
    +#+#
    0.54
    Activations Density 0.924%

    No Known Activations