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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 11036
    Prev
    Next
    INDEX
    Explanations

    references to sections or subsections in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    🏻
    -0.86
    BagLayout
    -0.85
    velopes
    -0.83
    ustainable
    -0.80
    ]--;
    -0.79
    Amicalement
    -0.76
    allible
    -0.74
    IsPostBack
    -0.71
    ampingi
    -0.71
     Vem
    -0.71
    POSITIVE LOGITS
     section
    2.50
     Section
    2.29
     sections
    2.27
    Section
    2.20
     Sections
    2.13
     SECTION
    2.09
    Sections
    2.04
    SECTION
    2.00
    section
    1.91
     SECTIONS
    1.85
    Activations Density 0.120%

    No Known Activations