© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 42418
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "dip" or related actions involving dipping

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

    dip and dipping

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     htmlFor
    -0.56
     stationnement
    -0.54
    fordert
    -0.52
    eventbus
    -0.50
    étoit
    -0.50
     voulons
    -0.50
     egens
    -0.50
    BrowserRouter
    -0.49
    UserScript
    -0.48
    NoSuchAlgorithm
    -0.48
    POSITIVE LOGITS
     dip
    1.02
     Dip
    1.01
     DIP
    0.99
    Dip
    0.99
     dipping
    0.91
    dip
    0.90
    DIP
    0.86
     dips
    0.85
     dipped
    0.76
     Diploma
    0.62
    Activations Density 0.007%

    No Known Activations