© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 409
    Prev
    Next
    INDEX
    Explanations

    elements related to Java programming, particularly methods and their declarations

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

    links to Java class methods and related Java programming content

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

    language identifiers

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    zyms
    -0.53
     zero
    -0.50
     koper
    -0.49
    ToDecimal
    -0.49
    філь
    -0.47
    zero
    -0.47
    preduce
    -0.46
    ütte
    -0.45
    SearchTree
    -0.45
    OWSKI
    -0.44
    POSITIVE LOGITS
    lang
    1.28
     lang
    1.15
     Lang
    1.10
    Lang
    1.07
    LANG
    1.00
     language
    0.93
     LANG
    0.90
     langue
    0.89
     defaultstate
    0.89
     Langford
    0.89
    Activations Density 0.029%

    No Known Activations