© 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. 9232
    Prev
    Next
    INDEX
    Explanations

    formal greetings and introductions in discussions

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

    the beginning-of-sequence position (i.e., the start of a document).

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

    the beginning of a document (start token).

    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
    发表于
    -0.56
    時から
    -0.54
    Communist
    -0.49
     lenker
    -0.48
    Ubuntu
    -0.47
     Prisons
    -0.47
    NLP
    -0.47
    BW
    -0.46
     energ
    -0.46
    iru
    -0.46
    POSITIVE LOGITS
     zijne
    0.67
     faptul
    0.66
     gevolg
    0.63
     myö
    0.63
     belangrij
    0.61
     atve
    0.60
     esfuer
    0.60
     dezelve
    0.59
     biß
    0.58
     zelve
    0.58
    Activations Density 0.537%

    No Known Activations