© 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. 9243
    Prev
    Next
    INDEX
    Explanations

    statements that express doubt or contradiction

    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
     zwar
    -0.45
     persönlichen
    -0.40
    虽
    -0.38
    虽然
    -0.36
     möglichst
    -0.35
     teniendo
    -0.35
    ながらも
    -0.34
    さすがに
    -0.34
    雖
    -0.34
    ::~
    -0.33
    POSITIVE LOGITS
     look
    1.37
     guess
    1.36
     remember
    1.34
     Look
    1.31
    look
    1.27
    Look
    1.27
    Remember
    1.20
     Remember
    1.20
    Guess
    1.16
     LOOK
    1.14
    Activations Density 0.463%

    No Known Activations