Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 5290
    Prev
    Next
    INDEX
    Explanations

    attributes and characteristics related to family structure and parental roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zeiti
    -0.32
     proved
    -0.28
    ningarna
    -0.28
     Regie
    -0.27
     HasFactory
    -0.27
    LEIA
    -0.26
    پیوند
    -0.26
     mitään
    -0.26
    nodoc
    -0.26
     berikutnya
    -0.25
    POSITIVE LOGITS
    rungsseite
    0.72
     وتسجيلات
    0.71
    новништво
    0.68
     ſind
    0.68
     فريبيس
    0.68
    
    0.68
     indígen
    0.64
    лтамалар
    0.63
     erſt
    0.62
     للاسماء
    0.62
    Activations Density 0.541%

    No Known Activations