© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4477
    Prev
    Next
    INDEX
    Explanations

    programming structures related to loops and conditionals

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

    Incrementing within a loop

    np_acts-logits-general · gemini-2.0-flash

    loop completion block start

    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
    CppCodeGen
    -0.52
    actionMode
    -0.51
    engo
    -0.50
    Explanation
    -0.49
    ándola
    -0.49
    ブラ
    -0.49
    ########.
    -0.49
    éndolo
    -0.48
     justific
    -0.47
    Спо
    -0.47
    POSITIVE LOGITS
    Referències
    0.81
    __':
    
    0.77
    queryInterface
    0.69
     typelib
    0.68
    ++){
    0.68
     hinweg
    0.67
     esternos
    0.65
    Personendaten
    0.65
    ticides
    0.64
    tagHelperRunner
    0.64
    Activations Density 0.064%

    No Known Activations