© 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. 7380
    Prev
    Next
    INDEX
    Explanations

    specific terms and phrases related to dates, programming functions, and identification codes

    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
     Ja
    -0.41
     Jaco
    -0.39
    Ja
    -0.36
     ja
    -0.35
     jam
    -0.33
    ja
    -0.32
     Jab
    -0.32
    я
    -0.31
    UnityEngine
    -0.30
    Gia
    -0.30
    POSITIVE LOGITS
     ju
    2.28
     Ju
    2.27
    Ju
    2.17
     JU
    2.00
     JUL
    1.96
    ju
    1.88
     Julian
    1.84
     Julie
    1.82
     Juli
    1.81
     Julius
    1.80
    Activations Density 0.727%

    No Known Activations