© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 8044
    Prev
    Next
    INDEX
    Explanations

    specific types of import statements and file management commands in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nasium
    -0.65
     disponibilités
    -0.65
    ChildScrollView
    -0.63
     TextInputType
    -0.62
     Mawr
    -0.59
    PRWEB
    -0.57
     meis
    -0.56
     TimeUnit
    -0.54
    UserScript
    -0.54
    ServletContext
    -0.53
    POSITIVE LOGITS
     <=",
    0.92
    findpost
    0.78
    ViewImports
    0.77
    expandindo
    0.69
     resourceCulture
    0.66
     دیکھیے
    0.62
    +:+
    0.58
    клопе
    0.56
    سطس
    0.55
     årene
    0.53
    Activations Density 0.045%

    No Known Activations