© 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. 412
    Prev
    Next
    INDEX
    Explanations

    code snippets or functions related to string manipulation and handling in programming

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

    function declarations and variable return types in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     Jérusalem
    -0.52
     urbain
    -0.49
    JoinColumn
    -0.47
     fixé
    -0.46
     Hinton
    -0.46
     médical
    -0.45
    وانه
    -0.45
     gratuitamente
    -0.45
    atelyn
    -0.43
     цен
    -0.42
    POSITIVE LOGITS
    queryInterface
    0.91
     typelib
    0.78
     disambiguazione
    0.74
    elemField
    0.70
    OGND
    0.67
    tagHelperRunner
    0.67
     Guid
    0.65
    rungsseite
    0.65
    脚注の使い方
    0.64
     OLE
    0.63
    Activations Density 0.205%

    No Known Activations