© 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. 40-GEMMASCOPE-RES-16K
    11. 6406
    Prev
    Next
    INDEX
    Explanations

    repeated mentions of the word "many" and its variations, indicating a focus on quantities or frequency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     noen
    -0.52
     some
    -0.48
     anything
    -0.46
     några
    -0.45
    some
    -0.45
     always
    -0.44
    certain
    -0.44
    always
    -0.43
    Certain
    -0.43
     Certain
    -0.43
    POSITIVE LOGITS
     different
    1.16
    different
    0.95
     thousands
    0.94
    Different
    0.90
     verschiedene
    0.88
    不同的
    0.86
     różnych
    0.85
     verschiedenen
    0.84
     facets
    0.84
    thousands
    0.82
    Activations Density 0.201%

    No Known Activations