© 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. 38-GEMMASCOPE-RES-16K
    11. 7527
    Prev
    Next
    INDEX
    Explanations

    references to local collaboration and community involvement in youth programs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mijne
    -0.80
     voeten
    -0.65
     zijne
    -0.63
     dezelve
    -0.59
     vermogen
    -0.57
     cumplido
    -0.56
     gewel
    -0.51
     geschenk
    -0.50
     gevallen
    -0.50
     escuchado
    -0.50
    POSITIVE LOGITS
    Dutch
    0.98
     Dutch
    0.96
    etera
    0.93
     Groningen
    0.90
     Utrecht
    0.86
     Eindhoven
    0.85
     dutch
    0.83
     enthousi
    0.83
     Rotterdam
    0.82
     webshop
    0.82
    Activations Density 0.358%

    No Known Activations