© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4414
    Prev
    Next
    INDEX
    Explanations

    references to specific varieties of crops or agricultural produce

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

    following a partial word (typo)

    np_acts-logits-general · gemini-2.0-flash

    Suplumfiftythree

    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
     didst
    -0.43
     results
    -0.40
     preventiva
    -0.40
    Étape
    -0.40
     argint
    -0.39
     accompli
    -0.39
     typical
    -0.39
     kancel
    -0.37
     Pflicht
    -0.37
     piele
    -0.37
    POSITIVE LOGITS
     useRouter
    0.57
    AISSEE
    0.49
    apatalk
    0.48
    izedBox
    0.48
    transQ
    0.47
     '\\;'
    0.47
     ObjectParameter
    0.47
    IUrlHelper
    0.46
    sandalia
    0.45
    adaptiveStyles
    0.45
    Activations Density 1.031%

    No Known Activations