© 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. 9-GEMMASCOPE-RES-16K
    11. 9534
    Prev
    Next
    INDEX
    Explanations

    elements related to sports scores and match outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ThroughAttribute
    -0.65
    出版年
    -0.59
    водства
    -0.57
    #![
    -0.54
     وتسجيلات
    -0.52
    CppCodeGen
    -0.51
    ScopeManager
    -0.49
    NavController
    -0.49
    AccessorTable
    -0.48
    Према
    -0.48
    POSITIVE LOGITS
     Equal
    0.69
     equal
    0.69
     igual
    0.67
     EQUAL
    0.66
     Igual
    0.65
     stalemate
    0.65
    Equal
    0.59
    unisex
    0.59
    equal
    0.58
     identically
    0.57
    Activations Density 0.568%

    No Known Activations