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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 1-GEMMASCOPE-RES-16K
    6. 13866
    Prev
    Next
    INDEX
    Explanations

    code snippets and references to programming concepts, particularly involving exceptions, URIs, and testing frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⓧ
    -0.71
     happened
    -0.68
     متعلقه
    -0.64
    happened
    -0.63
    readString
    -0.56
    nemia
    -0.55
     receivers
    -0.54
    sumowanie
    -0.52
     Verw
    -0.52
    initWithFrame
    -0.51
    POSITIVE LOGITS
    GroupLayout
    1.02
     насељу
    0.80
     Wikimedijinoj
    0.69
    PointerException
    0.63
     saites
    0.61
     simpat
    0.57
     समीक्षाओं
    0.55
     OFDb
    0.54
    kubectl
    0.53
    فحة
    0.52
    Activations Density 2.096%

    No Known Activations