© 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. 5375
    Prev
    Next
    INDEX
    Explanations

    instances of the "foreach" loop and related programming constructs

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

    Iterating through lists, sometimes with "foreach."

    np_acts-logits-general · gemini-2.0-flash

    `foreach` loop constructs

    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
    1
    -0.45
    a
    -0.45
    ナ
    -0.44
    natives
    -0.42
     issued
    -0.42
     held
    -0.42
     предела
    -0.41
     
    -0.41
     erfüllen
    -0.41
    n
    -0.41
    POSITIVE LOGITS
    foreach
    0.90
     CreateTagHelper
    0.87
    })*/
    0.84
    ISupport
    0.84
     foreach
    0.82
     Quanto
    0.80
    AddTagHelper
    0.80
     تضيفلها
    0.78
    <tbody>
    0.78
    $}}
    0.75
    Activations Density 0.030%

    No Known Activations