© 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. 22-GEMMASCOPE-RES-16K
    6. 7118
    Prev
    Next
    INDEX
    Explanations

    words related to children and their characteristics or statuses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rumbo
    -0.57
    retudo
    -0.52
    })=\
    -0.52
     &___
    -0.52
     linkovi
    -0.50
    ']))
    
    -0.49
     Beno
    -0.48
    }))
    
    -0.48
    \}=\
    -0.48
     geral
    -0.47
    POSITIVE LOGITS
    Child
    1.12
     Child
    1.10
    child
    0.96
     child
    0.95
     Children
    0.94
    Children
    0.93
     CHILD
    0.91
     getChild
    0.90
    getChild
    0.88
     Childs
    0.83
    Activations Density 0.098%

    No Known Activations