© 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. 25-GEMMASCOPE-RES-16K
    11. 4992
    Prev
    Next
    INDEX
    Explanations

    patterns or structures within sequences of characters, particularly focusing on specific character combinations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    a
    -1.01
    c
    -0.80
    d
    -0.69
    f
    -0.60
    e
    -0.58
     C
    -0.58
    s
    -0.52
    t
    -0.51
    خصة
    -0.49
    RegressionTest
    -0.48
    POSITIVE LOGITS
    MessageOf
    0.81
    SourceChecksum
    0.79
    TagMode
    0.66
     ProtoMessage
    0.65
     ویکی‌پدی
    0.61
     Paglinawan
    0.58
     famí
    0.57
     Viitattu
    0.56
     incontr
    0.55
    (!__
    0.54
    Activations Density 0.187%

    No Known Activations