© 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. 16-GEMMASCOPE-RES-65K
    11. 31647
    Prev
    Next
    INDEX
    Explanations

    discussions related to legal obligations and environmental management

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

    mitigation and proposals

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     defaultstate
    -0.73
    Revenir
    -0.62
    ерез
    -0.59
     >=",
    -0.59
    出版年
    -0.58
    liesslich
    -0.56
     amyloid
    -0.56
    TagHelper
    -0.54
    scienti
    -0.53
    ",{
    -0.53
    POSITIVE LOGITS
    BASELINE
    0.59
     proposed
    0.57
     Mitigation
    0.56
     DBNull
    0.54
     mitigation
    0.54
    Mitigation
    0.52
    proposed
    0.51
     proponent
    0.49
     aastal
    0.49
     Proposed
    0.48
    Activations Density 0.061%

    No Known Activations