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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 4-GEMMASCOPE-RES-16K
    6. 3136
    Prev
    Next
    INDEX
    Explanations

    programming constructs or code snippets related to memory operations and multi-threading

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SharedDtor
    -0.80
     NUKAT
    -0.70
    rrggbb
    -0.63
    principalColumn
    -0.63
    TextAppearance
    -0.62
    UrlResolution
    -0.61
     оригіналу
    -0.60
    tonode
    -0.60
    DeleteBehavior
    -0.60
     Testamento
    -0.59
    POSITIVE LOGITS
    EndInit
    0.88
    ViewFeatures
    0.67
     חיצוניים
    0.65
    Références
    0.63
     références
    0.61
     createState
    0.59
     externes
    0.56
     nonatomic
    0.56
     ***!
    0.55
    WebServlet
    0.54
    Activations Density 0.744%

    No Known Activations