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. 13313
    Prev
    Next
    INDEX
    Explanations

    names of people, particularly those involved in research or public services

    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
    bootstrapcdn
    -0.65
    TagMode
    -0.56
     cab
    -0.55
    CUSS
    -0.53
     SwitchCompat
    -0.51
    sidemargin
    -0.50
    داً
    -0.49
    omock
    -0.49
     Win
    -0.49
    addComponent
    -0.49
    POSITIVE LOGITS
    GEBURTSDATUM
    0.68
    .";
    
    0.62
    riwal
    0.62
    icestershire
    0.60
    Sharma
    0.59
    ècie
    0.59
    󠁣
    0.59
    .")
    
    0.57
     Приступљено
    0.56
    مصادر
    0.55
    Activations Density 0.199%

    No Known Activations