© 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-2-2B
    7. Residual Stream - 16k
    9. 8-GEMMASCOPE-RES-16K
    11. 13254
    Prev
    Next
    INDEX
    Explanations

    organizations and companies related to media production and publishing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monfieur
    -0.99
     purpoſe
    -0.86
     ainfi
    -0.85
     auffi
    -0.85
     myſelf
    -0.83
     CHAPITRE
    -0.83
     themſelves
    -0.82
     pouvoit
    -0.78
     againſt
    -0.78
     fhew
    -0.78
    POSITIVE LOGITS
     Inc
    0.68
     LLC
    0.65
     &
    0.57
    ,
    0.53
     Ltd
    0.52
    inc
    0.51
     Solutions
    0.49
     
    0.49
     Corp
    0.47
     (
    0.46
    Activations Density 0.274%

    No Known Activations