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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 11039
    Prev
    Next
    INDEX
    Explanations

    C++ programming constructs, particularly header file inclusions and `using` declarations

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

    C++ include statements

    np_acts-logits-general · gemini-2.0-flash

    C++ includes and usings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SourceChecksum
    -0.59
    httphttps
    -0.49
    ]=>
    -0.48
     Censo
    -0.46
     ویکی‌پدی
    -0.46
    
    -0.46
    новниш
    -0.45
    MessageOf
    -0.45
     calendriers
    -0.44
    tanleria
    -0.44
    POSITIVE LOGITS
     autorytatywna
    0.43
    MemoryWarning
    0.43
     BrowserModule
    0.39
    CppMethod
    0.38
    piratory
    0.37
    WireFormatLite
    0.37
    providedIn
    0.36
     humanas
    0.36
     umane
    0.35
    LLYWOOD
    0.33
    Activations Density 0.034%

    No Known Activations