© 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. 33-GEMMASCOPE-RES-16K
    11. 12029
    Prev
    Next
    INDEX
    Explanations

    details about events or activities occurring during specific time periods or seasons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     незавершена
    -0.73
    oa̍t
    -0.66
     kaarangay
    -0.63
    IVEREF
    -0.62
     snippetHide
    -0.62
     AppCompatTheme
    -0.61
     صوتيه
    -0.60
     Paglinawan
    -0.60
    SaveChangesAsync
    -0.60
     <>",
    -0.58
    POSITIVE LOGITS
    今年
    1.90
    今年は
    1.88
    今年の
    1.56
    今年も
    1.52
     diesmal
    1.38
    今回は
    1.32
    这次
    1.27
     heuer
    1.23
    這次
    1.21
    这一次
    1.21
    Activations Density 0.724%

    No Known Activations