© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15943
    Prev
    Next
    INDEX
    Explanations

    functions and data manipulation processes in code

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

    Code related to GUI or data manipulation

    np_acts-logits-general · gemini-2.0-flash

    function calls or assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    <()>
    -0.81
     {}".
    -0.61
     {}'.
    -0.59
    >().
    -0.56
    RegistryLite
    -0.54
    ={}
    -0.53
    umpulkan
    -0.51
     />
    -0.50
    ('/');
    -0.50
    <>();
    -0.50
    POSITIVE LOGITS
    BeginContext
    0.89
    ("",
    0.74
     >=",
    0.71
     nahilalakip
    0.71
    WebVitals
    0.68
     onResponse
    0.67
    verifyException
    0.66
    Décès
    0.66
    CGRectMake
    0.64
     الرياضيه
    0.64
    Activations Density 0.219%

    No Known Activations