© 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. 5737
    Prev
    Next
    INDEX
    Explanations

    policy-related terms and references in academic or technical writing

    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
     eye
    -0.62
     Eye
    -0.61
    Eye
    -0.59
    eye
    -0.56
    EYE
    -0.52
     EYE
    -0.52
    AnchorStyles
    -0.51
    眼
    -0.44
    RunWith
    -0.44
    disposing
    -0.43
    POSITIVE LOGITS
    expandindo
    0.51
     Grüsse
    0.41
     Flasche
    0.40
     Vereinbarung
    0.39
     personnalisée
    0.37
    PLANATION
    0.37
     дописавши
    0.37
    jores
    0.36
    Хьажоргаш
    0.36
    autaire
    0.36
    Activations Density 1.171%

    No Known Activations