© 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-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 15144
    Prev
    Next
    INDEX
    Explanations

    references to the prefix "ge" and related terms, particularly in the context of economics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    klärt
    -0.52
     odd
    -0.47
    prägt
    -0.45
    faßt
    -0.45
     complejidad
    -0.42
    ChildScrollView
    -0.41
     andet
    -0.40
    Kedua
    -0.39
     referirse
    -0.39
     rarity
    -0.39
    POSITIVE LOGITS
     Ge
    0.64
     ge
    0.60
    Ge
    0.59
    Geb
    0.48
     geo
    0.48
     GE
    0.46
    providedIn
    0.46
     Geos
    0.46
     Geo
    0.45
    ge
    0.45
    Activations Density 0.173%

    No Known Activations