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. 4794
    Prev
    Next
    INDEX
    Explanations

    references to programming languages and frameworks

    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
    )";
    
    -1.22
    "])
    
    -1.11
     Theſe
    -1.11
     ―――――
    -1.07
     crdi
    -1.05
    )");
    
    -1.04
     itſelf
    -1.03
    "]);
    
    -1.02
    LEncoder
    -1.02
     Мексичка
    -1.01
    POSITIVE LOGITS
    php
    0.87
    
    0.66
    ↵
    0.61
     (
    0.59
    ↵↵
    0.59
    -
    0.59
    .
    0.58
    ,
    0.58
    <eos>
    0.57
    badlogic
    0.53
    Activations Density 0.103%

    No Known Activations