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. 13-GEMMASCOPE-RES-16K
    6. 15361
    Prev
    Next
    INDEX
    Explanations

    instances of formatting elements or structures in text, such as code or mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    曖昧さ回避
    -0.78
    CONSIN
    -0.73
     calendriers
    -0.71
    :✨
    -0.70
     Wikimedijinoj
    -0.68
    ERVIEW
    -0.67
     ujednoznacz
    -0.67
    NamedQueries
    -0.66
    richTextPanel
    -0.64
    featureID
    -0.64
    POSITIVE LOGITS
    Fixed
    0.43
     viceversa
    0.42
    umb
    0.40
     pade
    0.39
    /
    
    0.38
    łaści
    0.38
    .
    
    0.38
    ưỡi
    0.38
    とき
    0.37
     Deixe
    0.37
    Activations Density 0.176%

    No Known Activations