© 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. 8636
    Prev
    Next
    INDEX
    Explanations

    references to a sequence or collection of items

    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
     tissue
    -0.53
     Tissue
    -0.49
    Tissue
    -0.49
    tissue
    -0.48
     Conference
    -0.47
    Conference
    -0.47
     conference
    -0.46
    conference
    -0.44
     Tissues
    -0.44
     tissues
    -0.43
    POSITIVE LOGITS
     series
    2.02
    Series
    1.86
    series
    1.86
     SERIES
    1.84
     Series
    1.84
    SERIES
    1.67
     série
    1.54
     séries
    1.47
     serie
    1.43
    シリーズ
    1.28
    Activations Density 0.059%

    No Known Activations