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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104544
    Prev
    Next
    INDEX
    Explanations

    concepts related to spirituality and the interconnectedness of beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الحره
    -0.56
     Wikimedijinoj
    -0.55
    Personensuche
    -0.55
    MessageOf
    -0.55
    脚注の使い方
    -0.53
     Away
    -0.53
     informée
    -0.52
     fuelled
    -0.52
     Depend
    -0.52
     disambiguazione
    -0.50
    POSITIVE LOGITS
     jüdis
    0.48
     judíos
    0.44
     Jewish
    0.40
     judiciales
    0.40
     Hebrew
    0.39
    Rabbi
    0.37
     Rabbi
    0.36
    Hebrew
    0.36
     extranjera
    0.34
     Jews
    0.33
    Activations Density 0.008%

    No Known Activations