© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 5825
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to compliance with criteria and requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -0.65
    
    -0.63
    قایناقلار
    -0.62
     Lexicon
    -0.56
     Италијани
    -0.55
    ніципалі
    -0.55
     Normdatei
    -0.54
     resourceCulture
    -0.54
     connotation
    -0.53
    %</
    -0.51
    POSITIVE LOGITS
     meets
    1.87
     meet
    1.87
     satisfy
    1.69
     satisfies
    1.69
     meeting
    1.64
     comply
    1.64
    meet
    1.63
     complies
    1.59
     fulfill
    1.55
     Meet
    1.53
    Activations Density 0.543%

    No Known Activations