© 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. 17-GEMMASCOPE-RES-16K
    11. 5696
    Prev
    Next
    INDEX
    Explanations

    patterns of class definitions and constructor functions in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    тку
    -0.50
    sizePolicy
    -0.48
     quoique
    -0.44
     Xuân
    -0.42
    ear
    -0.41
     concorso
    -0.41
    ه
    -0.39
    ={()=>
    -0.38
     بار
    -0.38
     ύ
    -0.38
    POSITIVE LOGITS
    super
    1.61
     super
    1.51
     SUPER
    1.19
    Super
    1.10
    SUPER
    1.09
     Super
    1.09
     súper
    1.02
    Superclass
    0.87
     супер
    0.86
    uper
    0.85
    Activations Density 0.066%

    No Known Activations