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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 16076
    Prev
    Next
    INDEX
    Explanations

    Python import statements related to the React library and its components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RectangleBorder
    -0.63
    findpost
    -0.58
    ReusableCell
    -0.57
    MLLoader
    -0.54
    StartTag
    -0.53
     saites
    -0.53
    ством
    -0.52
    mtable
    -0.51
     open
    -0.48
     ویکی‌آمباردا
    -0.48
    POSITIVE LOGITS
     enfans
    0.69
     polaire
    0.65
     Whig
    0.64
     âmes
    0.64
     Dumont
    0.64
     ainfi
    0.64
     pitää
    0.63
    ंदीखरीदारी
    0.63
     prière
    0.60
     conquête
    0.60
    Activations Density 0.045%

    No Known Activations