© 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. 61584
    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
    RefNanny
    -0.65
    WebServlet
    -0.63
    errHandler
    -0.60
    parsedMessage
    -0.59
    addGap
    -0.57
    enumii
    -0.56
    NamedQuery
    -0.56
    RSpec
    -0.55
    AxisAlignment
    -0.54
    modelBuilder
    -0.54
    POSITIVE LOGITS
     izd
    4.16
     изд
    1.22
     vyd
    0.85
     wyd
    0.79
     изда
    0.71
     Roskov
    0.63
     linkovi
    0.59
    oa̍t
    0.59
     issued
    0.57
     issuing
    0.57
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.