© 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. 41-GEMMASCOPE-RES-16K
    11. 10510
    Prev
    Next
    INDEX
    Explanations

    references to the user or direct address to the reader

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.62
    TagMode
    -0.46
    GOTREF
    -0.45
    UrlResolution
    -0.43
     пусть
    -0.42
    AndEndTag
    -0.42
    esez
    -0.41
    AddTagHelper
    -0.40
     soit
    -0.40
     decir
    -0.40
    POSITIVE LOGITS
     plan
    0.68
     wish
    0.68
     prefer
    0.68
     suspect
    0.67
     decide
    0.66
     happen
    0.57
     intend
    0.56
     like
    0.52
     require
    0.51
    enumi
    0.50
    Activations Density 0.200%

    No Known Activations