© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 12477
    Prev
    Next
    INDEX
    Explanations

    references to family and familial relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Two
    -0.89
    Two
    -0.87
     Thousands
    -0.81
    Thousands
    -0.78
     thousands
    -0.78
    thousands
    -0.78
     двух
    -0.73
    这两
    -0.71
    Hundreds
    -0.71
    TWO
    -0.69
    POSITIVE LOGITS
     nine
    2.11
     eight
    2.11
     seven
    2.09
     six
    1.98
     eleven
    1.83
     five
    1.73
     twelve
    1.71
    eight
    1.71
     thirteen
    1.70
    seven
    1.66
    Activations Density 1.046%

    No Known Activations