© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 180
    Prev
    Next
    INDEX
    Explanations

    greeting phrases and polite expressions

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    Followed by salutations or closings

    np_acts-logits-general · gemini-2.0-flash

    email openings and greetings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    stateMutability
    -0.63
    awtextra
    -0.62
     kasarigan
    -0.61
     cherchés
    -0.57
    UserScript
    -0.57
    EndInit
    -0.55
    ----</
    -0.54
    adaptiveStyles
    -0.54
    enderror
    -0.51
     BoxFit
    -0.50
    POSITIVE LOGITS
     LETTERS
    0.37
     lettre
    0.36
    AnimationsModule
    0.35
     lettera
    0.34
    éez
    0.33
     bahía
    0.33
    tionalität
    0.33
     greetings
    0.32
     lettres
    0.31
    Geografie
    0.31
    Activations Density 0.165%

    No Known Activations