© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 12447
    Prev
    Next
    INDEX
    Explanations

    complex adjectives and descriptors related to clarity and detail

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

    Adjectives describing a situation or thing

    np_acts-logits-general · gemini-2.0-flash

    describing qualities of discrete items

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     poszczegól
    -0.66
     Öffnungszeiten
    -0.64
     eivät
    -0.64
     rând
    -0.61
     autorité
    -0.60
     intenção
    -0.59
     kanssa
    -0.59
     Wohnungen
    -0.59
     idéia
    -0.59
     inmediata
    -0.58
    POSITIVE LOGITS
     basket
    0.59
     ſte
    0.57
     bundle
    0.55
     ſta
    0.53
     handful
    0.53
     Patro
    0.53
    twimg
    0.52
     piece
    0.52
     packet
    0.51
     palette
    0.51
    Activations Density 1.311%

    No Known Activations