© 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. 31503
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Liên
    -0.94
     Terraria
    -0.68
    Referanser
    -0.53
    quelize
    -0.48
     contextLoads
    -0.48
    database
    -0.48
    Database
    -0.47
    клопе
    -0.47
    gdx
    -0.47
    ItemBackground
    -0.46
    POSITIVE LOGITS
    청
    2.81
     청
    1.37
    IUrlHelper
    1.18
    록
    0.70
    addCriterion
    0.61
    허
    0.57
    fjspx
    0.57
    庁
    0.54
    LookAnd
    0.51
    참고
    0.51
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.