© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14932
    Prev
    Next
    INDEX
    Explanations

    repeated numeric patterns or sequences

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

    Alphanumeric characters and symbols

    np_acts-logits-general · gemini-2.0-flash

    numbers followed by words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    2
    -0.59
    1
    -0.58
    0
    -0.55
    3
    -0.51
     plus
    -0.49
    9
    -0.48
    7
    -0.47
     e
    -0.47
    5
    -0.47
     thousands
    -0.47
    POSITIVE LOGITS
     itſelf
    0.92
     ་་
    0.91
     propOrder
    0.90
     Efq
    0.88
    AddTagHelper
    0.85
    InjectAttribute
    0.85
     myſelf
    0.85
    IsMutable
    0.84
     Chriftian
    0.83
    writeFieldEnd
    0.82
    Activations Density 0.222%

    No Known Activations