© 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. 1105
    Prev
    Next
    INDEX
    Explanations

    code-related terms, particularly those associated with function definitions and variable manipulations

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

    Code related to updating or refreshing

    np_acts-logits-general · gemini-2.0-flash

    update and refresh actions

    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
    WebControls
    -0.60
    ftagPool
    -0.58
    SequentialGroup
    -0.58
    
    -0.58
    Marry
    -0.56
    tagHelperRunner
    -0.55
     AssemblyCulture
    -0.54
    ண்
    -0.51
    ंदीखरीदारी
    -0.51
     parting
    -0.49
    POSITIVE LOGITS
     recal
    1.20
     update
    1.15
    update
    1.07
     refresh
    1.06
     Update
    1.04
    refresh
    1.03
     updating
    1.00
     updated
    0.99
    Update
    0.99
     refreshed
    0.97
    Activations Density 0.234%

    No Known Activations