© 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. 16-GEMMASCOPE-RES-16K
    11. 16377
    Prev
    Next
    INDEX
    Explanations

    elements related to JSON structure and data types

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

    Code or configuration snippets

    np_acts-logits-general · gemini-2.0-flash

    this case

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rington
    -0.55
    -
    -0.53
     Kle
    -0.51
    orten
    -0.48
     their
    -0.47
    ני
    -0.47
     let
    -0.47
    chio
    -0.47
     mit
    -0.47
    år
    -0.47
    POSITIVE LOGITS
    LookAnd
    1.07
    
    0.98
    PerformLayout
    0.98
     NSCoder
    0.88
    parsedMessage
    0.87
    OGND
    0.87
     himo
    0.87
     CreateTagHelper
    0.85
    XmlAccessType
    0.85
    ContentAsync
    0.85
    Activations Density 0.098%

    No Known Activations