© 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. 34-GEMMASCOPE-RES-16K
    11. 15281
    Prev
    Next
    INDEX
    Explanations

    references to writing or correspondence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     enfans
    -1.55
     Menschheit
    -1.54
     Sünde
    -1.48
     Männern
    -1.47
     Füßen
    -1.44
     Geſch
    -1.43
     Geruch
    -1.40
     miniaturka
    -1.38
     mijne
    -1.38
     Feinde
    -1.38
    POSITIVE LOGITS
     ver
    0.63
     sch
    0.58
     hin
    0.56
     mit
    0.55
     neu
    0.55
     vers
    0.54
     dyna
    0.54
     sel
    0.53
     ge
    0.52
     potenti
    0.52
    Activations Density 0.197%

    No Known Activations