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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 12-GEMMASCOPE-RES-16K
    6. 15446
    Prev
    Next
    INDEX
    Explanations

    elements and attributes related to data handling in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AsUp
    -0.68
     Administrativna
    -0.68
    Cubit
    -0.65
     getattr
    -0.57
    memoized
    -0.57
     PropTypes
    -0.57
    Memento
    -0.57
    Према
    -0.56
    resave
    -0.56
     appuy
    -0.55
    POSITIVE LOGITS
    setVerticalGroup
    0.87
    AddHtmlAttribute
    0.59
    IndentedString
    0.53
     algu
    0.52
     BeautifulSoup
    0.51
    RenderAtEndOf
    0.50
     utafitiHapana
    0.49
    Multiline
    0.49
     rewritten
    0.48
     entire
    0.48
    Activations Density 0.397%

    No Known Activations