© 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. 20-GEMMASCOPE-RES-131K
    6. 63659
    Prev
    Next
    INDEX
    Explanations

    elements or modifiers indicating importance or emphasis, particularly through formatting like bold or strong text

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

    schedule pages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    -
    -0.37
     التر
    -0.37
    ########.
    -0.36
    SF
    -0.36
    how
    -0.35
    Ing
    -0.34
     الص
    -0.34
    Q
    -0.34
     düşünü
    -0.33
    ING
    -0.33
    POSITIVE LOGITS
     ویکی‌پدی
    0.66
     propOrder
    0.59
     مرئيه
    0.58
    OGND
    0.57
     ""],
    0.56
     oprot
    0.56
    ፩
    0.55
     AssemblyProduct
    0.54
     pajero
    0.52
    SharedDtor
    0.52
    Activations Density 0.018%

    No Known Activations