© 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. 4475
    Prev
    Next
    INDEX
    Explanations

    segments of code related to error handling and parsing in programming

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

    Objective-C class allocation and initialization

    np_acts-logits-general · gemini-2.0-flash

    Objective-C/Swift object initialization

    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
    MENAFN
    -0.63
     AssemblyCulture
    -0.54
    
    -0.53
    CloseOperation
    -0.47
     muerto
    -0.47
     poisoning
    -0.47
     Formación
    -0.46
    ValueStyle
    -0.46
    WriteTagHelper
    -0.43
     Signalez
    -0.43
    POSITIVE LOGITS
     ModelExpression
    0.68
    তথ্যসূত্র
    0.58
    égard
    0.58
    Tikang
    0.58
     tartalomajánló
    0.56
    ardless
    0.55
     perform
    0.54
    ,”
    0.54
    DAOImpl
    0.54
    '])->
    0.53
    Activations Density 0.181%

    No Known Activations