© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 31003
    Prev
    Next
    INDEX
    Explanations

    references to background images in code related to user interface design

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

    COLOR_BACKGROUND

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kháu
    -0.54
     ReactDOM
    -0.50
    WebVitals
    -0.47
    SharedDtor
    -0.47
     HasFactory
    -0.46
    MemoryWarning
    -0.46
    MessageTagHelper
    -0.46
    ‫
    -0.46
    :✨
    -0.45
    Demografía
    -0.45
    POSITIVE LOGITS
     background
    1.33
    background
    1.17
     backgrounds
    1.15
     BACKGROUND
    1.10
     Background
    1.09
    Background
    1.05
     Hintergrund
    1.02
    BACKGROUND
    0.98
     배경
    0.97
     backdrop
    0.94
    Activations Density 0.029%

    No Known Activations