© 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. 0-GEMMASCOPE-RES-16K
    11. 13540
    Prev
    Next
    INDEX
    Explanations

    repeated instances of the term "chi" in a scientific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſtate
    -0.76
     ſta
    -0.73
     faſt
    -0.72
     MainAxisSize
    -0.70
     ſont
    -0.65
     ſind
    -0.64
     Monfieur
    -0.64
     myſelf
    -0.63
     ſte
    -0.63
    expandindo
    -0.62
    POSITIVE LOGITS
    [-
    0.81
    -(
    0.55
     ik
    0.54
    ik
    0.53
    __(/*!
    0.49
    IK
    0.47
     '{
    0.47
    ({
    0.44
     (*
    0.44
    ordinary
    0.43
    Activations Density 0.443%

    No Known Activations