© 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
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 6838
    Prev
    Next
    INDEX
    Explanations

    Boolean values indicating truthfulness or falseness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cass
    -0.55
     paras
    -0.53
     fossa
    -0.51
    ConstraintMaker
    -0.50
     scrat
    -0.50
     Bote
    -0.50
    tshell
    -0.49
     CIG
    -0.49
    "},
    
    -0.48
    `/
    -0.48
    POSITIVE LOGITS
     true
    1.92
    true
    1.75
     True
    1.63
    True
    1.57
     TRUE
    1.52
    TRUE
    1.45
     verdadero
    1.10
     verdadeiro
    1.06
     verdadera
    1.06
     truest
    1.05
    Activations Density 0.082%

    No Known Activations