© 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. 24-GEMMASCOPE-RES-16K
    11. 8919
    Prev
    Next
    INDEX
    Explanations

    specific programming languages and their constructs, particularly focusing on commands, functions, and syntax specific to coding

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

    Comparison operators (>, <, =, etc.)

    np_acts-logits-general · gemini-2.0-flash

    comparison operators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    بوابة
    -0.56
    Autoritní
    -0.51
    DockStyle
    -0.50
     تضيفلها
    -0.49
    styleType
    -0.47
     mou
    -0.47
    kannt
    -0.47
    jud
    -0.46
    Према
    -0.46
     ***!
    -0.46
    POSITIVE LOGITS
     eq
    0.93
    eq
    0.88
     equal
    0.87
     >=",
    0.87
     Equal
    0.86
     greater
    0.84
     gt
    0.79
    gt
    0.78
     <=",
    0.78
     EQUAL
    0.78
    Activations Density 0.331%

    No Known Activations