© 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 EvalsExportsinterp-engineNEWAPI 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. 7337
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notations related to functions and sets

    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
     Keys
    -0.72
     Ке
    -0.66
    KS
    -0.65
    Ks
    -0.63
    KES
    -0.63
    KER
    -0.63
    Keys
    -0.62
    Ker
    -0.62
     Key
    -0.61
    CK
    -0.60
    POSITIVE LOGITS
     k
    0.96
     king
    0.72
     ki
    0.67
     kit
    0.65
     kid
    0.64
    k
    0.64
     к
    0.61
     kind
    0.59
     הק
    0.59
     الك
    0.56
    Activations Density 0.900%

    No Known Activations