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. 11-GEMMASCOPE-RES-16K
    6. 6332
    Prev
    Next
    INDEX
    Explanations

    code-related symbols and syntax in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BeginContext
    -0.71
    )");
    
    -0.70
    ness
    -0.66
    fromLTRB
    -0.65
    "।
    -0.63
    GEBURTSDATUM
    -0.60
    ity
    -0.60
    enumii
    -0.59
    //{
    
    -0.58
    "{\
    -0.57
    POSITIVE LOGITS
     giapp
    0.65
     aéri
    0.64
    rungsseite
    0.64
     leçons
    0.63
     étr
    0.62
     bénéfices
    0.60
     vettor
    0.60
     dieux
    0.60
     Inorg
    0.59
     religieuses
    0.59
    Activations Density 0.933%

    No Known Activations