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 Post
    5. 12-GEMMASCOPE-RES-1M
    6. 384
    Prev
    Next
    INDEX
    Explanations

    structural elements of programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_1m/average_l0_107
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    1,048,576
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     škoda
    -0.57
    blazer
    -0.55
     búsquedas
    -0.54
    rupulous
    -0.52
    vernight
    -0.49
     maît
    -0.49
    üglich
    -0.48
    CHASE
    -0.48
    +][
    -0.48
    änglich
    -0.48
    POSITIVE LOGITS
    tagHelperRunner
    0.86
     TestBed
    0.70
    ChildScrollView
    0.63
    WaitGroup
    0.61
     насељу
    0.61
     BrowserModule
    0.60
    InjectAttribute
    0.58
    VersionUID
    0.56
    期刊论文
    0.56
    expandindo
    0.55
    Activations Density 0.000%

    No Known Activations