© 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. 4165
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and formal statements involving variables and functions

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

    Ends with a period, close parenthesis, or close brace

    np_acts-logits-general · gemini-2.0-flash

    mathematical or structured text delimiters

    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
     even
    -0.64
     white
    -0.55
     finalized
    -0.52
     même
    -0.52
     infra
    -0.52
     Source
    -0.50
    llung
    -0.50
     Solid
    -0.49
    Alte
    -0.49
     nog
    -0.49
    POSITIVE LOGITS
     ComVisible
    0.89
     esternos
    0.87
    tagext
    0.86
     мәкал
    0.80
     становника
    0.79
    aarrggbb
    0.77
    adaptiveStyles
    0.73
     propOrder
    0.70
     externi
    0.69
    Искәрмәләр
    0.68
    Activations Density 0.947%

    No Known Activations