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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 16-GEMMASCOPE-RES-16K
    6. 2890
    Prev
    Next
    INDEX
    Explanations

    sentence structures or specific punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     صوتيه
    -0.89
     StatefulWidget
    -0.81
    ]--;
    -0.72
     ✭✭
    -0.67
    orale
    -0.64
     intptr
    -0.63
     MessageBoxIcon
    -0.61
     StatelessWidget
    -0.61
    IsContent
    -0.61
    -------------</
    -0.60
    POSITIVE LOGITS
    Basically
    0.63
    Итак
    0.62
     Basically
    0.57
    sätzlich
    0.56
    是这样的
    0.54
    Essentially
    0.53
    diğinde
    0.51
    Firstly
    0.50
     folgendes
    0.50
    Regarding
    0.49
    Activations Density 0.364%

    No Known Activations