© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 1659
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals and their familial relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     popular
    -0.33
     Aufs
    -0.31
     management
    -0.30
     خ
    -0.29
     forms
    -0.29
     rec
    -0.29
     base
    -0.28
     increments
    -0.28
     offres
    -0.28
     solution
    -0.28
    POSITIVE LOGITS
    transQ
    0.74
    homonymie
    0.63
     indígen
    0.62
     laſſen
    0.61
     incrí
    0.60
     témoig
    0.59
    Personensuche
    0.59
     autorytatywna
    0.59
    MLLoader
    0.59
     betweenstory
    0.58
    Activations Density 0.658%

    No Known Activations