© 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. 9-GEMMASCOPE-RES-16K
    11. 16309
    Prev
    Next
    INDEX
    Explanations

    references to academic or scientific publication details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eff
    -0.55
     glisser
    -0.49
     chúng
    -0.48
     lược
    -0.48
     quietly
    -0.48
     tids
    -0.47
    γο
    -0.46
    ízo
    -0.46
     disant
    -0.46
    玲
    -0.44
    POSITIVE LOGITS
    TagMode
    1.08
    StoryboardSegue
    0.90
    verwijspagina
    0.89
    oredCriteria
    0.88
    enderror
    0.82
     noDo
    0.81
     disambiguazione
    0.78
     صوتيه
    0.78
     ModelExpression
    0.76
     Мексичка
    0.76
    Activations Density 0.282%

    No Known Activations