© 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. 31-GEMMASCOPE-RES-16K
    11. 10279
    Prev
    Next
    INDEX
    Explanations

    phrases related to social connections and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases indicating social interaction and meeting with groups of people.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ब्रेकडाउन
    -0.71
    enterOuterAlt
    -0.70
    reportWebVitals
    -0.56
    KommentareTeilen
    -0.54
    WriteTagHelper
    -0.50
    bidities
    -0.49
    <?
    -0.48
    申し訳
    -0.48
    expandindo
    -0.48
     ligiloj
    -0.47
    POSITIVE LOGITS
     fellow
    1.28
     sesama
    0.98
    fellow
    0.94
    Fellow
    0.93
     Fellow
    0.80
     FELLOW
    0.77
     kindred
    0.76
     peers
    0.73
     strangers
    0.65
     compatriots
    0.54
    Activations Density 0.315%

    No Known Activations