© 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. 11726
    Prev
    Next
    INDEX
    Explanations

    references to piezoelectric materials or concepts

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

    ending in "ie" or "pie"

    np_acts-logits-general · gemini-2.0-flash

    words starting with ie, pie, sie, vie

    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
    __*/
    -0.90
    KommentareTeilen
    -0.82
    izr
    -0.75
    ckner
    -0.71
     تضيفلها
    -0.71
     Zorn
    -0.68
    তথ্যসূত্র
    -0.65
    casian
    -0.64
    انيف
    -0.64
    ylvan
    -0.63
    POSITIVE LOGITS
    Rie
    1.14
     Gie
    1.12
    IE
    1.06
    ie
    1.05
     Fie
    1.05
     Arie
    1.02
     Hie
    1.02
     pies
    0.99
     Pie
    0.98
     PIE
    0.97
    Activations Density 0.309%

    No Known Activations