© 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. 38-GEMMASCOPE-RES-16K
    11. 14860
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the prevalence or majority of a certain group or opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Gambas
    -0.38
    
    -0.34
    #+#
    -0.34
    RTHOOK
    -0.33
    ніципа
    -0.33
    ならでは
    -0.32
    一系列
    -0.30
     ciel
    -0.29
     peine
    -0.29
    олові
    -0.29
    POSITIVE LOGITS
     majority
    3.77
    majority
    3.36
    Majority
    3.00
     Majority
    2.81
     majorité
    2.47
     maioria
    2.42
     mayoría
    2.39
     Mehrheit
    2.34
     maggior
    1.95
     большин
    1.95
    Activations Density 0.752%

    No Known Activations