© 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 - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 4867
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns related to family or close relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     decidedly
    -0.54
    typically
    -0.53
     kasarigan
    -0.48
    Clearly
    -0.48
    неопр
    -0.48
    ulously
    -0.45
    AISSEE
    -0.44
    fuge
    -0.43
     admittedly
    -0.42
     wohl
    -0.41
    POSITIVE LOGITS
     defaultstate
    0.50
     own
    0.49
     equipments
    0.49
     another
    0.47
     dear
    0.47
     selve
    0.47
     stuffs
    0.46
     candidature
    0.45
     favourite
    0.44
     Excellency
    0.44
    Activations Density 0.258%

    No Known Activations