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. 4094
    Prev
    Next
    INDEX
    Explanations

    specific data entries or references that indicate academic or scientific information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the beginning of a new text segment, especially the start-of-sequence marker.

    oai_token-act-pair · gpt-5Triggered by @timna
    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
     мәкал
    -0.82
    gdx
    -0.80
    ⓧ
    -0.78
     pinulongan
    -0.77
    consulté
    -0.77
    tableFuture
    -0.76
     apellidos
    -0.74
    MLLoader
    -0.73
    Šaltiniai
    -0.72
     propOrder
    -0.72
    POSITIVE LOGITS
     يتيمه
    0.58
     المعيارى
    0.52
     चुनें
    0.49
     otomatig
    0.48
    ContextHolder
    0.48
    كويكب
    0.47
     चीज़ों
    0.45
    __
    0.43
     armée
    0.42
     sovereignty
    0.42
    Activations Density 1.140%

    No Known Activations