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

    mathematical operations and calculations

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

    Mathematical formulas with fractions and exponents

    np_acts-logits-general · gemini-2.0-flash

    fractions and halves

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    athyroid
    -0.45
    IVEREF
    -0.43
     system
    -0.41
    __()
    -0.40
     MTV
    -0.39
     multi
    -0.39
    thodon
    -0.39
     has
    -0.38
    system
    -0.38
    literals
    -0.37
    POSITIVE LOGITS
    half
    1.30
     half
    1.29
    Half
    1.24
     Half
    1.20
     HALF
    1.15
    HALF
    1.11
     halves
    0.98
     mitad
    0.97
     Hälfte
    0.96
     halfway
    0.94
    Activations Density 0.494%

    No Known Activations