© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 14291
    Prev
    Next
    INDEX
    Explanations

    numerical values and measurements in a technical context, particularly related to CSS and layout design

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

    CSS sizing units (px, %, pt, vmin, vh, rem, vw)

    np_acts-logits-general · gemini-2.0-flash

    css units like px and percent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.58
    Tracce
    -0.54
     препратки
    -0.52
    stateProvider
    -0.51
    riwal
    -0.50
    principalTable
    -0.50
     estekak
    -0.49
    lesias
    -0.48
     CWE
    -0.48
    expandindo
    -0.48
    POSITIVE LOGITS
    px
    1.21
    PX
    0.86
     px
    0.75
    vmin
    0.72
    vh
    0.70
    %;
    0.68
    rem
    0.67
    %!
    0.66
     PX
    0.66
    vw
    0.66
    Activations Density 0.107%

    No Known Activations