Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 707
    Prev
    Next
    INDEX
    Explanations

    structured programming elements and property definitions in code

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

    Code containing brackets and parentheses

    np_acts-logits-general · gemini-2.0-flash

    code assignment or return

    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
     
    -0.38
     par
    -0.37
     re
    -0.35
    спита
    -0.35
     over
    -0.35
    //
    -0.34
     via
    -0.33
     or
    -0.33
     val
    -0.32
     e
    -0.32
    POSITIVE LOGITS
     InputDecoration
    1.34
    
    1.07
     propOrder
    1.06
    CodedInputStream
    1.04
     BoxDecoration
    1.02
    RegistryLite
    1.00
    ThroughAttribute
    1.00
    rungsseite
    0.98
     المعيارى
    0.98
     GenerationType
    0.98
    Activations Density 0.587%

    No Known Activations