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. 12-GEMMASCOPE-RES-16K
    6. 1979
    Prev
    Next
    INDEX
    Explanations

    references to class types and hierarchies in programming or classification contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     uſed
    -1.00
     poffible
    -1.00
     neceffary
    -0.96
     withal
    -0.94
     poffe
    -0.92
     Monfieur
    -0.88
     juſt
    -0.87
     pleaſure
    -0.86
     Reſ
    -0.85
     ſeveral
    -0.83
    POSITIVE LOGITS
     Class
    1.72
     class
    1.61
     CLASS
    1.55
     classes
    1.54
    Class
    1.47
    class
    1.46
    classnames
    1.37
     Classes
    1.36
    CLASS
    1.36
    classes
    1.30
    Activations Density 0.086%

    No Known Activations