© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 15227
    Prev
    Next
    INDEX
    Explanations

    geographic locations and bodies of water

    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
     ashore
    -0.42
     препратки
    -0.40
    MessageTagHelper
    -0.39
     PopupWindow
    -0.39
     Ufer
    -0.38
    tagHelperRunner
    -0.38
    znym
    -0.36
    出版年
    -0.35
    комо
    -0.34
    matitis
    -0.33
    POSITIVE LOGITS
     ocean
    1.07
     oceans
    1.04
     sea
    0.89
     seas
    0.87
     océ
    0.85
     Atlantic
    0.84
    ocean
    0.84
     Ocean
    0.76
     biển
    0.75
    Atlantic
    0.73
    Activations Density 0.283%

    No Known Activations