© 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. 41-GEMMASCOPE-RES-16K
    11. 4243
    Prev
    Next
    INDEX
    Explanations

    phrases indicating possession or the existence of conditions or requirements

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    saw
    -0.64
    wrote
    -0.63
     blew
    -0.61
     drove
    -0.58
    went
    -0.56
     wrote
    -0.56
    fell
    -0.55
    took
    -0.54
    gave
    -0.53
    broke
    -0.53
    POSITIVE LOGITS
     been
    0.65
     little
    0.60
     difficulty
    0.59
     sought
    0.59
     reason
    0.59
     long
    0.57
     previously
    0.55
     considerable
    0.54
     tended
    0.54
     hitherto
    0.53
    Activations Density 0.422%

    No Known Activations