© 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. 100885
    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
    abbix
    -0.65
     Schmid
    -0.48
     Swanson
    -0.46
     Signal
    -0.46
     Helga
    -0.44
     Banco
    -0.44
    FERENCE
    -0.43
    Portail
    -0.43
    spf
    -0.43
    banco
    -0.43
    POSITIVE LOGITS
    getWriter
    4.72
    Writer
    0.76
    getOutputStream
    0.75
     Writer
    0.72
     writer
    0.71
    writer
    0.71
     Writers
    0.70
    Writers
    0.70
     writers
    0.67
    ResponseWriter
    0.66
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.