© 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. 8165
    Prev
    Next
    INDEX
    Explanations

    various references to "divisions" and related terms in structured formats

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

    the word "Div" appearing in technical or code contexts.

    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
     consultato
    -0.57
    Suerte
    -0.56
    RTLU
    -0.52
    ंदीखरीदारी
    -0.50
    PerformLayout
    -0.48
     viață
    -0.47
    butuhkan
    -0.46
    Datuak
    -0.45
     Separate
    -0.44
     fiscale
    -0.44
    POSITIVE LOGITS
     Div
    0.77
    Div
    0.67
     DIV
    0.63
     Division
    0.63
     Divide
    0.63
     divide
    0.61
     divides
    0.60
     divisão
    0.59
    Division
    0.59
     div
    0.59
    Activations Density 0.221%

    No Known Activations