© 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. 11790
    Prev
    Next
    INDEX
    Explanations

    instances of the word "boy" and its variations

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

    the word "boy" as an exclamation or intensifier (like "Boy, oh boy!").

    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
     EconPapers
    -0.63
     linkovi
    -0.56
     mergeFrom
    -0.53
    annica
    -0.47
    Autowired
    -0.44
     unknownFields
    -0.44
    BeginInit
    -0.44
    
    -0.43
     anhänger
    -0.42
     antidesliz
    -0.42
    POSITIVE LOGITS
    Boy
    0.83
     scouts
    0.78
     scout
    0.76
     Boy
    0.74
     Scouts
    0.72
    boy
    0.71
    boys
    0.67
     BOY
    0.66
     boys
    0.65
    Boys
    0.63
    Activations Density 0.071%

    No Known Activations