© 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
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 10898
    Prev
    Next
    INDEX
    Explanations

    phrases related to family and interfaith discussions

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

    formal, technical or procedural language about organizing structure—joining, separating, grouping elements, and planning or evaluating arrangements.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    words that express purpose, necessity, or means to accomplish something, particularly infinitive "to" phrases and modal expressions indicating what should, must, or can be done.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
     Hitam
    -0.45
     hitam
    -0.44
     invasión
    -0.40
    retudo
    -0.37
    fär
    -0.36
     Cię
    -0.36
     tebal
    -0.35
     Putih
    -0.35
     TAMBÉM
    -0.34
     sprawy
    -0.33
    POSITIVE LOGITS
    
    0.68
    rungsseite
    0.60
     EconPapers
    0.57
     transfieras
    0.56
    logrus
    0.56
    存于互联网档案馆
    0.54
     individual
    0.53
     nahilalakip
    0.52
     indiv
    0.51
    Portail
    0.51
    Activations Density 0.599%

    No Known Activations