© 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. 18-GEMMASCOPE-RES-16K
    11. 8791
    Prev
    Next
    INDEX
    Explanations

    programming-related structural elements, such as components and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code fragments (often C++ or Java)

    np_acts-logits-general · gemini-2.0-flash

    code blocks and SQL

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ffilm
    -0.74
    BibitemShut
    -0.73
    jestel
    -0.73
     transfieras
    -0.69
    qrstuvwxyz
    -0.67
     propOrder
    -0.66
    eaways
    -0.66
    bottomrule
    -0.66
    RegressionTest
    -0.66
    новништво
    -0.66
    POSITIVE LOGITS
        
    0.82
    0.74
            
    0.65
    　
    0.65
       
    0.63
    principalColumn
    0.63
    0.62
          
    0.58
         
    0.58
    　　
    0.57
    Activations Density 0.135%

    No Known Activations