© 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. 10520
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the structure of arguments or ideas, particularly those that organize content into parts or steps

    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
     infine
    -0.43
     Chwiliwch
    -0.38
    sidemargin
    -0.38
    ahrt
    -0.37
    läufig
    -0.37
     впер
    -0.36
    ={({
    -0.35
    RTSN
    -0.35
    Kanpo
    -0.34
    IsContent
    -0.34
    POSITIVE LOGITS
     second
    3.73
    second
    3.34
    Second
    3.23
     Second
    3.19
     SECOND
    2.97
    SECOND
    2.80
     segunda
    2.66
     secondly
    2.63
     segundo
    2.63
    第二
    2.61
    Activations Density 1.375%

    No Known Activations