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. 0-GEMMASCOPE-RES-16K
    6. 7982
    Prev
    Next
    INDEX
    Explanations

    references to 'mat' indicating visual framing or presentation elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     InputDecoration
    -0.63
    MergeFrom
    -0.62
    enseits
    -0.61
     ISNI
    -0.58
    Soorten
    -0.53
    
    -0.53
    stoj
    -0.52
     blijkt
    -0.52
     getNumber
    -0.52
     Forth
    -0.51
    POSITIVE LOGITS
     mat
    1.31
     mats
    1.15
    mat
    1.09
     MAT
    1.01
    GEBURTSDATUM
    1.00
    MAT
    0.98
    Mat
    0.94
     matt
    0.94
     MATT
    0.93
    matt
    0.92
    Activations Density 0.219%

    No Known Activations