© 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. 7090
    Prev
    Next
    INDEX
    Explanations

    mathematical notations related to functions and derivatives

    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
    /*
    -0.60
     betweenstory
    -0.47
    向
    -0.45
     privilege
    -0.43
    客
    -0.42
    multicolumn
    -0.42
     Extragalactic
    -0.42
    Ответить
    -0.41
     committee
    -0.41
     event
    -0.41
    POSITIVE LOGITS
    stood
    0.57
     itſelf
    0.56
     ujednoznacz
    0.55
     myſelf
    0.54
     Administrativna
    0.54
     zijne
    0.53
     mijne
    0.52
    AddTagHelper
    0.51
    setVerticalGroup
    0.51
    kapnya
    0.50
    Activations Density 0.489%

    No Known Activations