© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1190
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names

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

    Tokens after periods, parentheses, and brackets

    np_acts-logits-general · gemini-2.0-flash

    technical or academic references

    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
    -
    -0.51
     للاسماء
    -0.49
     PLWABN
    -0.48
     ljud
    -0.48
     épo
    -0.48
    AHUL
    -0.47
     emprego
    -0.47
     aktivitet
    -0.47
     selezione
    -0.46
     perigo
    -0.45
    POSITIVE LOGITS
    */;
    0.85
     referenties
    0.84
     BoxFit
    0.80
     ]
    
    0.75
     AssemblyCulture
    0.75
     Италијани
    0.74
     AssemblyCompany
    0.73
    URLException
    0.72
    MLElement
    0.72
     ddelweddau
    0.71
    Activations Density 0.186%

    No Known Activations