© 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. 31-GEMMASCOPE-RES-16K
    11. 3373
    Prev
    Next
    INDEX
    Explanations

    references to legal exceptions and regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    specific legal references and regulatory citations.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    テンツ
    -0.37
     تضيفلها
    -0.33
     layui
    -0.31
    ADX
    -0.31
     शी
    -0.30
     Redist
    -0.29
    most
    -0.28
    ụng
    -0.28
     useCallback
    -0.28
     фи
    -0.28
    POSITIVE LOGITS
     exceptions
    2.66
     exception
    2.50
     exemptions
    2.27
     Exceptions
    2.27
     exemption
    2.20
    例外
    2.00
     excepción
    1.98
    exceptions
    1.96
    Exceptions
    1.96
     Ausnahme
    1.91
    Activations Density 0.827%

    No Known Activations