© 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. 31-GEMMASCOPE-RES-131K
    11. 34962
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     worldwide
    -0.50
     internationales
    -0.43
     internation
    -0.43
     rumours
    -0.42
     colour
    -0.42
     international
    -0.41
     vapour
    -0.40
     EMEA
    -0.40
     colours
    -0.40
     coloured
    -0.40
    POSITIVE LOGITS
    AndEndTag
    0.58
     statewide
    0.57
    Filmografie
    0.56
    Respectfully
    0.53
    esri
    0.50
     Autorizaciones
    0.49
     Nonprofit
    0.49
    clusal
    0.49
     politici
    0.48
    Political
    0.48
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.