© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 1930
    Prev
    Next
    INDEX
    Explanations

    scientific terms and technical language related to experimental methods and data analysis

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    Numerical values followed by punctuation

    np_acts-logits-general · gemini-2.0-flash

    focal adhesion kinase

    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
    Negative Logits
    __(/*!
    -0.89
    Portail
    -0.61
    Sucesor
    -0.58
    WithMany
    -0.55
     Tch
    -0.54
    Портал
    -0.53
    XmlAccessType
    -0.52
     Ngb
    -0.52
     GAC
    -0.51
    MethodManager
    -0.51
    POSITIVE LOGITS
    RegressionTest
    0.61
     CreateTagHelper
    0.57
    isDebugEnabled
    0.54
    AndroidJUnit
    0.52
     والث
    0.51
    
    0.49
    apollo
    0.47
     taches
    0.47
     Réponses
    0.47
    HttpGet
    0.46
    Activations Density 0.336%

    No Known Activations