Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4609
    Prev
    Next
    INDEX
    Explanations

    structures or formatting in code or textual data

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

    preceding questions

    np_acts-logits-general · gemini-2.0-flash

    juvenile idiopathic artritis

    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
    NUMX
    -0.57
    WireFormatLite
    -0.56
    .";
    
    -0.54
     XNUMX
    -0.54
     $_"
    -0.53
    StateToProps
    -0.53
     lts
    -0.52
    bró
    -0.52
     Jum
    -0.51
     FN
    -0.51
    POSITIVE LOGITS
    UnsafeEnabled
    0.78
    ///</
    0.73
    الإنجليزية
    0.71
    	
    0.70
    		
    0.64
    Бахар
    0.64
     AssemblyCulture
    0.64
    rawDesc
    0.63
            
    0.62
             
    0.61
    Activations Density 0.053%

    No Known Activations