© 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. 34-GEMMASCOPE-RES-16K
    11. 11632
    Prev
    Next
    INDEX
    Explanations

    instances of the preposition "to"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SourceChecksum
    -0.49
     haberse
    -0.47
     laikā
    -0.44
     löyty
    -0.43
     šķ
    -0.43
     المعيارى
    -0.42
     '\\;'
    -0.42
    الدراسه
    -0.42
     okuyayım
    -0.42
     ocasião
    -0.42
    POSITIVE LOGITS
     bed
    0.70
     heaven
    0.69
     see
    0.65
     places
    0.62
     sleep
    0.62
     work
    0.59
     Italy
    0.55
     Europe
    0.54
     meetings
    0.54
     Heaven
    0.54
    Activations Density 0.257%

    No Known Activations