© 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. 18-GEMMASCOPE-RES-16K
    11. 4033
    Prev
    Next
    INDEX
    Explanations

    background and color properties in CSS or styling contexts

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

    CSS background properties

    np_acts-logits-general · gemini-2.0-flash

    background styling and section titles

    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
    baye
    -0.72
    ⮕
    -0.51
    cientos
    -0.51
     crowns
    -0.48
     Denkmal
    -0.48
    tor
    -0.48
    atars
    -0.47
    ocino
    -0.46
     souri
    -0.46
     besos
    -0.46
    POSITIVE LOGITS
    XmlAccessType
    0.83
    TintMode
    0.81
    EDEFAULT
    0.78
    BGM
    0.74
     bg
    0.74
     doInBackground
    0.72
     متعلقه
    0.71
    ItemBackground
    0.71
     backgrounds
    0.70
    Gemeinsame
    0.69
    Activations Density 0.067%

    No Known Activations