© 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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 74499
    Prev
    Next
    INDEX
    Explanations

    the use of assertions in testing code, particularly those that expect certain conditions to be true

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

    should return

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     Jenderal
    -0.56
     paſſ
    -0.48
    RegistryLite
    -0.45
    Autoritní
    -0.44
    fromnode
    -0.44
     صوتيه
    -0.44
     ſte
    -0.43
    engarkan
    -0.41
     ſur
    -0.41
     profesión
    -0.41
    POSITIVE LOGITS
    ˏ
    0.51
     nawr
    0.50
     auto
    0.48
     produce
    0.47
     permit
    0.47
     clean
    0.46
     effective
    0.46
    зовать
    0.46
     provide
    0.44
     Utility
    0.44
    Activations Density 0.005%

    No Known Activations