Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 6212
    Prev
    Next
    INDEX
    Explanations

    attributes and values related to CSS classes and IDs in HTML code

    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
    ThroughAttribute
    -0.97
     Monfieur
    -0.94
     myſelf
    -0.93
    mybatisplus
    -0.91
     raiſ
    -0.82
     kasarigan
    -0.82
     itſelf
    -0.82
    تقاوى
    -0.81
    EndContext
    -0.80
    Hochspringen
    -0.78
    POSITIVE LOGITS
    classnames
    1.12
    toggleClass
    0.88
    removeClass
    0.73
    addClass
    0.70
    hasClass
    0.70
    classList
    0.68
    className
    0.66
     Class
    0.61
     className
    0.60
    classname
    0.58
    Activations Density 0.167%

    No Known Activations