© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 66631
    Prev
    Next
    INDEX
    Explanations

    references to authors and contributors in academic or scientific texts

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

    names and ordinals

    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
     selfies
    -0.78
     emojis
    -0.76
     selfie
    -0.73
     للمعارف
    -0.72
     defaultstate
    -0.68
     incentiv
    -0.68
     microbiome
    -0.66
     emoji
    -0.64
     hashtags
    -0.62
     onboarding
    -0.62
    POSITIVE LOGITS
    faßt
    0.44
     daß
    0.41
    StringBuffer
    0.40
     muß
    0.38
     informée
    0.35
     Einfluß
    0.34
     StringBuffer
    0.32
     mußten
    0.32
    WithMany
    0.32
     Miß
    0.31
    Activations Density 0.158%

    No Known Activations