© 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. 3-GEMMASCOPE-RES-16K
    11. 6090
    Prev
    Next
    INDEX
    Explanations

    references to specific quantities, particularly the number twelve

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hyrchwyd
    -0.59
    Portail
    -0.54
    存于互联网档案馆
    -0.49
     
    -0.47
    ­
    -0.46
    egrave
    -0.44
     simplifié
    -0.44
     Obrador
    -0.44
    ־
    -0.44
    enumi
    -0.43
    POSITIVE LOGITS
     fourteen
    2.00
     twelve
    1.99
     thirteen
    1.96
     seventeen
    1.93
     eighteen
    1.93
     sixteen
    1.91
     fifteen
    1.89
     nineteen
    1.82
    twelve
    1.75
     eleven
    1.68
    Activations Density 0.179%

    No Known Activations