Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 10607
    Prev
    Next
    INDEX
    Explanations

    words and terms related to piezoelectricity and piezoelectric devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    KommentareTeilen
    -0.72
    Zeneca
    -0.71
     تضيفلها
    -0.70
    fully
    -0.69
    __*/
    -0.69
    انيف
    -0.69
    -------------</
    -0.66
    expandindo
    -0.64
    ckner
    -0.63
     gezet
    -0.63
    POSITIVE LOGITS
     Gie
    1.04
    ie
    1.03
     Arie
    1.03
    Rie
    1.02
     Hie
    1.02
     pies
    1.00
    IE
    0.99
     Fie
    0.96
     CIE
    0.95
     Pie
    0.95
    Activations Density 0.261%

    No Known Activations