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. 16-GEMMASCOPE-RES-16K
    6. 16022
    Prev
    Next
    INDEX
    Explanations

    mentions of hardware components and their configurations

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

    Hardware and microcontroller specifications

    np_acts-logits-general · gemini-2.0-flash

    microcontroller hardware and connectivity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     >=",
    -0.65
    ArrowToggle
    -0.58
    Obras
    -0.57
     Paglinawan
    -0.57
    bestos
    -0.56
    Sitemap
    -0.56
    ImageContext
    -0.55
     búsquedas
    -0.55
    rlpool
    -0.55
    makeConstraints
    -0.54
    POSITIVE LOGITS
     hardware
    0.66
     standalone
    0.63
    standalone
    0.60
     connected
    0.60
     equipped
    0.59
     onboard
    0.58
     module
    0.57
    equipped
    0.56
     modular
    0.56
     capabilities
    0.56
    Activations Density 0.621%

    No Known Activations