© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 10709
    Prev
    Next
    INDEX
    Explanations

    specific programming-related keywords and structures in code snippets

    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
    rdı
    -0.53
    ."</
    -0.51
     Romains
    -0.49
    ."<
    -0.48
     noix
    -0.48
    ...");
    
    -0.48
    గా
    -0.48
     getOrder
    -0.47
     "",
    
    -0.45
    ++
    
    -0.45
    POSITIVE LOGITS
    StoryboardSegue
    0.87
    lapsingToolbar
    0.77
     JpaRepository
    0.72
    ⓧ
    0.71
    RegistryLite
    0.70
    MemoryWarning
    0.69
     memoized
    0.68
    mybatisplus
    0.66
     protoimpl
    0.65
    Tikang
    0.65
    Activations Density 0.588%

    No Known Activations