© 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. 20-GEMMASCOPE-RES-16K
    11. 11738
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and expressions related to dimensionality and functions

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

    Mathematical notation/symbols

    np_acts-logits-general · gemini-2.0-flash

    fever Right

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    newInstance
    -0.44
    Php
    -0.41
     COVID
    -0.41
    ejs
    -0.40
    راع
    -0.39
    ]={
    -0.39
     dtype
    -0.38
     waar
    -0.37
    (&:
    -0.37
    serializers
    -0.37
    POSITIVE LOGITS
     Paglinawan
    0.91
     <=",
    0.89
     @"/
    0.88
    StructEnd
    0.87
    MLLoader
    0.86
    openConnection
    0.83
    writeFieldEnd
    0.83
     fieldNum
    0.80
     houſe
    0.80
     myſelf
    0.80
    Activations Density 1.218%

    No Known Activations