© 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. 439
    Prev
    Next
    INDEX
    Explanations

    semicolons and their associated syntax in code

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

    Java import statements and declarations, particularly those used for handling serialization and collections

    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
    Chham
    -0.67
     transfieras
    -0.65
    AddTagHelper
    -0.63
    يكب
    -0.57
    IonicModule
    -0.57
     NSCoder
    -0.56
    Източници
    -0.56
    ⓧ
    -0.55
    ണ്
    -0.53
    VIAF
    -0.53
    POSITIVE LOGITS
    RUnlock
    0.72
     Audiodateien
    0.60
    URLException
    0.57
    withstanding
    0.57
    uminescence
    0.56
    ]\\
    0.55
     correctes
    0.54
    kunde
    0.53
    _
    0.51
    }$.\\
    0.51
    Activations Density 0.009%

    No Known Activations