© 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. 8827
    Prev
    Next
    INDEX
    Explanations

    statements relating to the use of namespaces in programming code

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

    C++ "using namespace" statements

    np_acts-logits-general · gemini-2.0-flash

    using namespace

    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
    chengladbach
    -0.53
    jsonwebtoken
    -0.49
    bundet
    -0.48
     вовсе
    -0.47
     carteira
    -0.47
    ensement
    -0.46
    weiler
    -0.45
    Verifier
    -0.44
    owanej
    -0.42
     întâ
    -0.42
    POSITIVE LOGITS
     namespace
    1.16
     الحره
    1.02
     '\\;'
    0.94
    الحياه
    0.91
    rungsseite
    0.83
    tagHelperRunner
    0.77
    LookAnd
    0.72
    +#+#
    0.71
    
    0.71
     EconPapers
    0.71
    Activations Density 0.037%

    No Known Activations