© 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. 13346
    Prev
    Next
    INDEX
    Explanations

    specific scientific terminologies and concepts related to data and analysis

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

    Followed by prepositions

    np_acts-logits-general · gemini-2.0-flash

    technical and scientific terms

    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
    ValueGeneration
    -0.67
    WriteTagHelper
    -0.65
     unſer
    -0.65
     verſch
    -0.63
    XmlAccessorType
    -0.63
    elemField
    -0.63
    ſammen
    -0.62
     mergeFrom
    -0.62
    [@BOS@]
    -0.62
     fashiola
    -0.62
    POSITIVE LOGITS
     nisso
    0.33
     مُعرِّف
    0.32
     astfel
    0.32
    こう
    0.30
     isso
    0.30
    ↵↵
    0.28
     contigo
    0.28
    此
    0.28
    Transporte
    0.27
     
    0.27
    Activations Density 1.163%

    No Known Activations