© 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. 8078
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical structures and their properties, particularly in graph theory and algebra

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

    Mathematical notation with symbols

    np_acts-logits-general · gemini-2.0-flash

    mathematical set theory concepts

    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
    enumi
    -0.54
    +#+
    -0.54
    #+#
    -0.52
    いわ
    -0.49
     Near
    -0.47
    nvarchar
    -0.45
     Northern
    -0.45
    ✨:
    -0.45
    昨
    -0.45
    DebuggerNonUser
    -0.45
    POSITIVE LOGITS
     termica
    0.72
     denoted
    0.70
     $
    0.66
     ${\
    0.65
     avoient
    0.62
     $\
    0.61
     scolaires
    0.61
    ModelSerializer
    0.61
     quelcon
    0.61
     linguistique
    0.61
    Activations Density 1.826%

    No Known Activations