© 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. 27-GEMMASCOPE-RES-16K
    11. 6791
    Prev
    Next
    INDEX
    Explanations

    terms and phrases indicating improvement or advancement in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     enfans
    -0.49
     thingy
    -0.48
     chamber
    -0.45
     inconvénients
    -0.44
     prêtres
    -0.43
    contentLoaded
    -0.40
     peuples
    -0.40
     ſtate
    -0.40
     pères
    -0.40
    someone
    -0.39
    POSITIVE LOGITS
     reductions
    0.56
     versions
    0.54
     kinds
    0.54
     patterns
    0.54
     quantities
    0.52
     opportunities
    0.51
     implementations
    0.51
     levels
    0.51
     discussions
    0.51
     avenues
    0.51
    Activations Density 0.756%

    No Known Activations