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. 20-GEMMASCOPE-RES-16K
    6. 1232
    Prev
    Next
    INDEX
    Explanations

    CSS properties related to transformations and layout adjustments

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

    CSS prefixes (-moz, -webkit, -o)

    np_acts-logits-general · gemini-2.0-flash

    CSS `display` property and vendor prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagMode
    -0.68
     myſelf
    -0.67
    DataAnnotations
    -0.67
    enaire
    -0.63
    스터
    -0.59
    .'</
    -0.59
     виправивши
    -0.59
    isci
    -0.58
    vastava
    -0.57
    JoinColumn
    -0.57
    POSITIVE LOGITS
     IE
    0.75
     CSS
    0.60
    IE
    0.53
     browsers
    0.52
    PIE
    0.51
    CSS
    0.50
     Web
    0.50
    Moz
    0.50
    webkit
    0.50
     navigateur
    0.49
    Activations Density 0.396%

    No Known Activations