© 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. 16-GEMMASCOPE-RES-16K
    6. 3941
    Prev
    Next
    INDEX
    Explanations

    conditional compilation directives and attributes in code

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

    Code-related special characters and symbols

    np_acts-logits-general · gemini-2.0-flash

    code preprocessor directives (#ifndef, #if

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tangan
    -0.52
    Coordonnées
    -0.47
     réessayer
    -0.47
    RunWith
    -0.46
     Ahnung
    -0.46
    想想
    -0.46
    ExecuteReader
    -0.45
    PROBLE
    -0.45
    __":
    
    -0.44
    ientôt
    -0.44
    POSITIVE LOGITS
     चीज़ों
    0.74
     تضيفلها
    0.72
    kloped
    0.70
    NewUrlParser
    0.69
     لينك
    0.62
    openzeppelin
    0.59
     الحره
    0.59
    ьаж
    0.59
    zepine
    0.58
     оригіналу
    0.58
    Activations Density 0.431%

    No Known Activations