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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 22-GEMMASCOPE-RES-16K
    6. 3309
    Prev
    Next
    INDEX
    Explanations

    components of user interface design, specifically related to navigation elements like modals and dropdowns

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

    HTML elements or code snippets

    np_acts-logits-general · gemini-2.0-flash

    accordion body

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rasil
    -0.60
    GraphicsUnit
    -0.53
    principalColumn
    -0.51
     McNally
    -0.49
    ēju
    -0.49
    WarningLevel
    -0.49
    moil
    -0.48
    ibia
    -0.48
    Chham
    -0.48
     double
    -0.47
    POSITIVE LOGITS
     ExecuteAsync
    0.73
    IUrlHelper
    0.64
     JAXBElement
    0.61
    Body
    0.60
    body
    0.59
    header
    0.57
     header
    0.57
     footer
    0.56
     linkovi
    0.54
     body
    0.54
    Activations Density 0.106%

    No Known Activations