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. 5-GEMMASCOPE-RES-16K
    6. 1914
    Prev
    Next
    INDEX
    Explanations

    code structures and elements related to programming, particularly in C# applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.84
     Италијани
    -0.63
    ="";
    
    -0.61
    PreInfinity
    -0.60
    =[];
    
    -0.58
     paper
    -0.57
    =";
    -0.57
     StringTokenizer
    -0.57
    >";
    
    -0.56
    πού
    -0.55
    POSITIVE LOGITS
    tvguidetime
    0.96
     internetowa
    0.70
     AssemblyCompany
    0.67
     suivants
    0.66
     σή
    0.63
     bezeichneter
    0.63
    /*
    0.62
    enumi
    0.62
     versteht
    0.61
    .*")]
    0.60
    Activations Density 0.043%

    No Known Activations