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. 12892
    Prev
    Next
    INDEX
    Explanations

    keywords and attributes related to class and constructor definitions in programming languages

    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
    IndentedString
    -0.78
     ""],
    -0.66
    LookAnd
    -0.66
    TagMode
    -0.64
     ग्राहक
    -0.55
    Javadoc
    -0.54
    HomeAsUpEnabled
    -0.53
    RunWith
    -0.52
    .";
    
    -0.51
    ExtendWith
    -0.51
    POSITIVE LOGITS
    +#+
    0.58
     receitas
    0.54
    enderror
    0.52
     aastal
    0.52
    észet
    0.52
    asio
    0.49
    expandindo
    0.48
    fendi
    0.48
     frisch
    0.48
     recettes
    0.47
    Activations Density 0.110%

    No Known Activations