© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 11992
    Prev
    Next
    INDEX
    Explanations

    themes related to death and burial practices

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

    funeral and burial

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    cambrian
    -0.38
    podr
    -0.38
     rę
    -0.38
     multiplic
    -0.37
     sirup
    -0.36
     Bersama
    -0.36
     đế
    -0.35
    Multip
    -0.35
     multip
    -0.35
    Origin
    -0.35
    POSITIVE LOGITS
     funeral
    1.82
     burial
    1.73
     funerals
    1.57
     coffin
    1.55
     Funeral
    1.49
     Burial
    1.44
     burials
    1.42
     funer
    1.39
     burying
    1.34
    Funeral
    1.34
    Activations Density 0.051%

    No Known Activations