© 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. 31123
    Prev
    Next
    INDEX
    Explanations

    specific data patterns and numeric sequences in a tabular format

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

    hexadecimal numbers followed by comma

    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
    nam
    -0.54
    angu
    -0.52
     temp
    -0.50
    STRO
    -0.50
    joh
    -0.50
     log
    -0.49
    NOWLEDG
    -0.48
     DIRE
    -0.48
     Sdn
    -0.46
    DIRE
    -0.46
    POSITIVE LOGITS
    RegressionTest
    1.10
    DockStyle
    1.09
     kasarigan
    1.02
    RegistryLite
    0.97
     ExecuteAsync
    0.97
    TargetException
    0.96
     كومونز
    0.94
     AssemblyCompany
    0.93
     Normdatei
    0.90
    DoubleQuotes
    0.89
    Activations Density 0.060%

    No Known Activations