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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 9204
    Prev
    Next
    INDEX
    Explanations

    numerical data or statistics for comparison

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    3
    -0.46
    uerre
    -0.46
     Duncan
    -0.42
    崩
    -0.42
    inSlope
    -0.42
     Plaza
    -0.42
     three
    -0.41
    4
    -0.41
     email
    -0.40
    สาม
    -0.40
    POSITIVE LOGITS
    CloseOperation
    0.82
     fourteenth
    0.73
     fifteenth
    0.72
    RegressionTest
    0.70
     thirteenth
    0.69
     Fourteenth
    0.69
     Seventeenth
    0.69
     autorytatywna
    0.68
     otomatig
    0.68
     ddelweddau
    0.68
    Activations Density 0.478%

    No Known Activations