© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 3895
    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
    RetentionPolicy
    -0.50
    CreateModel
    -0.49
     étoient
    -0.45
    akterysty
    -0.45
     exhibición
    -0.43
     sitzt
    -0.42
     étoit
    -0.42
     refuer
    -0.40
     asamblea
    -0.40
     Byd
    -0.40
    POSITIVE LOGITS
    umented
    2.03
    Instrumented
    0.65
    addCriterion
    0.65
    NameInMap
    0.58
     instrumentation
    0.58
    лтамалар
    0.57
    Sucesor
    0.55
     Instrumentation
    0.53
     instr
    0.52
    AndroidJUnit
    0.51
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.