© 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. 14623
    Prev
    Next
    INDEX
    Explanations

    references to application programming interfaces (APIs) and their functionalities

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

    technical APIs and specifications

    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
     suun
    -0.54
     enamorado
    -0.50
    assemblée
    -0.50
     tarko
    -0.45
    mlung
    -0.44
     debilidad
    -0.43
    SaveChangesAsync
    -0.43
     étoit
    -0.42
    FormTagHelper
    -0.42
    ohjel
    -0.42
    POSITIVE LOGITS
     autorytatywna
    0.56
    DataAnnotations
    0.50
    Autoritní
    0.49
    :✨
    0.47
     ligiloj
    0.46
     ANSI
    0.45
     ieee
    0.44
    ########.
    0.43
     ISO
    0.42
    Tep
    0.42
    Activations Density 0.077%

    No Known Activations