© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 3915
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific findings and observations

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

    reporting observations and findings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     it
    -0.80
     about
    -0.64
    about
    -0.57
     It
    -0.56
    yip
    -0.54
    валі
    -0.53
    BeanFactory
    -0.53
    itti
    -0.53
    hyr
    -0.52
     its
    -0.52
    POSITIVE LOGITS
     насељу
    0.71
     ExecuteAsync
    0.71
     möjligt
    0.61
     raining
    0.60
     muligt
    0.59
    دانشنامهٔ
    0.59
    IonicModule
    0.58
    DataAnnotations
    0.58
     assumed
    0.57
    TextWatcher
    0.57
    Activations Density 0.087%

    No Known Activations