© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 31521
    Prev
    Next
    INDEX
    Explanations

    references to comparative results or data in studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    comparison phrases

    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
    Not in Any Lists

    No Comments

    Negative Logits
     oub
    -0.54
     Pab
    -0.54
     Crud
    -0.53
     Ży
    -0.52
    glEnd
    -0.52
     purpoſe
    -0.52
     Hamm
    -0.51
     JAXBElement
    -0.50
     SAB
    -0.50
    δας
    -0.50
    POSITIVE LOGITS
    TintMode
    0.68
    TargetException
    0.68
     McManus
    0.67
    findpost
    0.65
     ModelExpression
    0.64
    newArrayList
    0.64
     Himo
    0.62
     &___
    0.60
    iraj
    0.59
    Bibliograf
    0.59
    Activations Density 0.035%

    No Known Activations