© 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. 2-GEMMASCOPE-RES-16K
    11. 8547
    Prev
    Next
    INDEX
    Explanations

    mentions of legal statements or claims made during legal proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    niająca
    -0.45
    
    -0.42
    原始内容存档
    -0.41
    enderror
    -0.40
    CrossRef
    -0.40
    ItemBackground
    -0.40
    Vidite
    -0.39
    inWeight
    -0.38
     disambiguazione
    -0.38
    存于互联网档案馆
    -0.38
    POSITIVE LOGITS
     requests
    1.61
     statements
    1.48
     calls
    1.34
    requests
    1.34
     messages
    1.27
    Requests
    1.22
     claims
    1.20
     promises
    1.20
     queries
    1.20
     comments
    1.19
    Activations Density 0.348%

    No Known Activations