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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 52094
    Prev
    Next
    INDEX
    Explanations

    pronouns and demonstratives highlighting ownership or existence

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

    dates with numbers

    np_acts-logits-general · gemini-2.5-flash-lite

    indicators of conversation structure—special/control tokens marking start-of-sequence, start-of-turn, or the "user" role.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
    •list 2
    상대방에 대한 관심

    No Comments

    Negative Logits
     
    -0.62
     (
    -0.61
     and
    -0.52
     [
    -0.51
     or
    -0.48
     &
    -0.46
    _
    -0.45
     /
    -0.44
     et
    -0.44
     "
    -0.43
    POSITIVE LOGITS
     queſta
    1.10
     Administrativna
    1.09
     imagui
    1.08
    niſſe
    1.08
     beſch
    1.07
     verſch
    1.05
    ſicht
    1.05
     zwiſchen
    1.04
    <pad>
    1.03
    <unused51>
    1.03
    Activations Density 0.569%

    No Known Activations