© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 10050
    Prev
    Next
    INDEX
    Explanations

    instances of the word "lay" and its variations in different contexts

    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
     nahilalakip
    -0.51
    Personensuche
    -0.40
     EClass
    -0.37
     <<-
    -0.36
    unknownFields
    -0.35
    UnknownFieldSet
    -0.34
    脚注の使い方
    -0.34
    stdc
    -0.33
     recha
    -0.33
     ligiloj
    -0.33
    POSITIVE LOGITS
     claim
    0.75
     bare
    0.70
     groundwork
    0.66
     siege
    0.62
    claim
    0.62
     waste
    0.60
     fallow
    0.59
    Bare
    0.58
     dormant
    0.56
     Bare
    0.55
    Activations Density 0.194%

    No Known Activations