© 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. 351
    Prev
    Next
    INDEX
    Explanations

    function calls and their parameters in code

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

    Code or identifiers

    np_acts-logits-general · gemini-2.0-flash

    list manipulation

    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
      
    -0.68
     
    -0.61
     con
    -0.60
       
    -0.52
    ↵↵↵↵↵
    -0.51
    ↵↵↵↵
    -0.50
    ↵↵↵
    -0.50
     in
    -0.49
    adaran
    -0.48
     
    -0.47
    POSITIVE LOGITS
     nakalista
    0.81
     للاسماء
    0.79
    LookAnd
    0.76
     AssemblyProduct
    0.74
     članak
    0.73
     ujednoznacz
    0.71
    لينكات
    0.69
    InstrumentedTest
    0.68
    НИК
    0.65
    berdayakan
    0.64
    Activations Density 0.131%

    No Known Activations