© 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. 40-GEMMASCOPE-RES-16K
    11. 2129
    Prev
    Next
    INDEX
    Explanations

    technical language and specifications related to devices and systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    //
    -0.43
     Taktlose
    -0.43
    しかも
    -0.42
    endida
    -0.41
     zwar
    -0.40
    자인
    -0.38
    either
    -0.37
    言うと
    -0.37
    unanje
    -0.36
    ՝
    -0.36
    POSITIVE LOGITS
     etc
    4.00
    etc
    3.19
     Etc
    2.97
    Etc
    2.88
     usw
    2.66
    等等
    2.50
     등
    2.45
    等
    2.44
     ect
    2.39
     आदि
    2.19
    Activations Density 1.452%

    No Known Activations