© 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. 11-GEMMASCOPE-RES-16K
    11. 5231
    Prev
    Next
    INDEX
    Explanations

    references to summation and calculations involving totals

    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
     للاسماء
    -0.73
     Infórmanos
    -0.69
    majánló
    -0.57
     kasarigan
    -0.57
     BrowserModule
    -0.56
     Administrativna
    -0.55
     HasFactory
    -0.55
     ligiloj
    -0.55
    waltung
    -0.54
     utafitiHapana
    -0.54
    POSITIVE LOGITS
     sum
    0.68
     summing
    0.63
     Sum
    0.59
     sums
    0.59
    Summing
    0.58
    sum
    0.58
    Sum
    0.56
    Sums
    0.54
     합
    0.53
     Summe
    0.52
    Activations Density 1.123%

    No Known Activations