© 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. 31-GEMMASCOPE-RES-16K
    11. 3196
    Prev
    Next
    INDEX
    Explanations

    keywords related to pharmacology and social demographics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word "pharmaco" and related pharmaceutical/pharmacological terminology.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DOCTYPE
    -0.40
     kanal
    -0.35
     kated
    -0.35
    }}</
    -0.33
     Tenga
    -0.32
     gelang
    -0.31
     Normdatei
    -0.31
    expliquer
    -0.31
     matang
    -0.31
     Monographs
    -0.30
    POSITIVE LOGITS
    EndContext
    0.58
    /**
    0.57
     transfieras
    0.57
    webElementXpaths
    0.54
    Biographie
    0.54
    enderror
    0.53
    yakarta
    0.49
    dafx
    0.49
     <>",
    0.49
    httphttps
    0.48
    Activations Density 0.570%

    No Known Activations