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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 4470
    Prev
    Next
    INDEX
    Explanations

    elements related to style and design in code

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

    HTML style attributes

    np_acts-logits-general · gemini-2.0-flash

    style attribute syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     odkazy
    -0.76
    expandindo
    -0.74
    Източници
    -0.72
    Vanjske
    -0.71
    Välislingid
    -0.68
     tartalomajánló
    -0.66
    ebenarnya
    -0.65
    Portail
    -0.65
    LookAnd
    -0.64
     himo
    -0.63
    POSITIVE LOGITS
    styleUrls
    0.59
     StatelessWidget
    0.56
    ={{
    0.52
    WebElementEntity
    0.49
    JNIEnv
    0.48
    owanego
    0.47
    relate
    0.47
     CGRectMake
    0.46
     SwiftUI
    0.46
     itemprop
    0.46
    Activations Density 0.029%

    No Known Activations