© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 7496
    Prev
    Next
    INDEX
    Explanations

    terms related to workshops and persons involved in events or studies

    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
     humans
    -0.41
    vantage
    -0.40
     contextLoads
    -0.40
     Humans
    -0.38
    Humans
    -0.36
     humains
    -0.35
    gener
    -0.35
     للبيع
    -0.35
    Newswire
    -0.34
    tldr
    -0.33
    POSITIVE LOGITS
     workshop
    1.03
     Workshop
    0.93
    Workshop
    0.91
    workshop
    0.91
     workshops
    0.87
     Workshops
    0.81
     WORKSHOP
    0.79
    Workshops
    0.74
     persons
    0.64
     nahilalakip
    0.61
    Activations Density 0.047%

    No Known Activations