© 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 - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 10389
    Prev
    Next
    INDEX
    Explanations

    phrases related to problems or mistakes in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     alcanzó
    -0.49
    送到
    -0.46
     yapılır
    -0.44
     अनु
    -0.44
     sağlar
    -0.42
    written
    -0.42
     najdete
    -0.41
     pouce
    -0.41
     insecticide
    -0.41
     dons
    -0.41
    POSITIVE LOGITS
    tvguidetime
    1.00
     autorytatywna
    0.97
     going
    0.93
     making
    0.92
     getting
    0.85
     doing
    0.84
     looking
    0.81
     giving
    0.80
    はじめに
    0.79
     taking
    0.79
    Activations Density 0.259%

    No Known Activations