© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 40-GEMMASCOPE-RES-16K
    11. 5761
    Prev
    Next
    INDEX
    Explanations

    elements related to data input and form submissions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     нього
    -0.47
     неё
    -0.41
    nya
    -0.39
    ]-'
    -0.36
     kanya
    -0.35
    ICOLON
    -0.35
     iyo
    -0.35
     її
    -0.35
     shown
    -0.35
     ними
    -0.34
    POSITIVE LOGITS
     в
    0.94
     для
    0.92
     и
    0.82
     с
    0.79
     или
    0.75
     на
    0.73
     через
    0.65
     из
    0.63
    XmlAccessorType
    0.63
     как
    0.62
    Activations Density 0.008%

    No Known Activations