© 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. 7886
    Prev
    Next
    INDEX
    Explanations

    conditional phrases indicating uncertainty or nuance in statements

    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
     either
    -0.83
     Either
    -0.82
    Either
    -0.78
     malah
    -0.78
     even
    -0.78
     además
    -0.75
    either
    -0.75
     EVEN
    -0.73
     invece
    -0.73
     moreover
    -0.71
    POSITIVE LOGITS
     technically
    1.30
     initially
    1.20
     nominally
    1.17
     admittedly
    1.14
     ostensibly
    1.03
    Initially
    1.01
     theoretically
    0.98
     superfic
    0.98
     inicialmente
    0.98
     Initially
    0.97
    Activations Density 0.593%

    No Known Activations