© 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 EvalsExportsAPI 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. 29918
    Prev
    Next
    INDEX
    Explanations

    academic and professional qualifications

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

    technical identifiers

    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
     loja
    -0.51
     Dear
    -0.45
    Dear
    -0.44
     effects
    -0.43
     Buon
    -0.42
     Vereinigte
    -0.42
     Effects
    -0.41
     Open
    -0.41
     pos
    -0.40
    Patho
    -0.40
    POSITIVE LOGITS
    GEBURTSDATUM
    0.86
     Мексичка
    0.85
    WithIOException
    0.81
     TextAppearance
    0.80
    RegressionTest
    0.77
    ValueStyle
    0.77
    lapsingToolbar
    0.76
    存于互联网档案馆
    0.74
     createState
    0.74
    RegistryLite
    0.73
    Activations Density 0.031%

    No Known Activations