© 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. 0-GEMMASCOPE-RES-16K
    11. 1882
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'many'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    少数
    -0.60
    と思ったら
    -0.54
     Quelques
    -0.54
     paar
    -0.53
     ſta
    -0.52
     handful
    -0.52
     slate
    -0.50
     Preferences
    -0.48
    sprit
    -0.48
    셈
    -0.48
    POSITIVE LOGITS
     much
    2.23
     many
    2.22
    Much
    1.98
    much
    1.95
    many
    1.84
     Much
    1.84
     mucho
    1.83
     muchos
    1.71
     muchas
    1.70
    Many
    1.62
    Activations Density 0.334%

    No Known Activations