© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 7864
    Prev
    Next
    INDEX
    Explanations

    sequential phrases indicating the passage of time

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     snippetHide
    -0.53
     propOrder
    -0.47
    ValueGenerated
    -0.45
     pleaſure
    -0.44
    лтамалар
    -0.44
    ClientRect
    -0.44
    Kích
    -0.44
     beginnetje
    -0.43
     PeEnEo
    -0.42
    Cryptography
    -0.42
    POSITIVE LOGITS
     later
    1.43
    later
    1.39
    Later
    1.36
     Later
    1.35
     später
    1.29
     LATER
    1.14
     späteren
    1.09
     позже
    1.09
     senere
    1.06
     później
    1.02
    Activations Density 0.304%

    No Known Activations