© 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. 38-GEMMASCOPE-RES-16K
    11. 12254
    Prev
    Next
    INDEX
    Explanations

    phrases related to conspiracy or coordinated actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bateman
    -0.47
    ástica
    -0.43
     Marche
    -0.43
     Wiseman
    -0.42
    DebuggerNonUser
    -0.42
    setVerticalGroup
    -0.41
     Mooney
    -0.41
     McFadden
    -0.41
     Blackman
    -0.40
     thiện
    -0.40
    POSITIVE LOGITS
    tor
    1.48
     tor
    1.41
    Tor
    1.38
     Tor
    1.36
     TOR
    1.34
    TOR
    1.34
     Tori
    1.13
    ator
    1.11
     tors
    1.10
    itor
    1.09
    Activations Density 0.920%

    No Known Activations