© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 40-GEMMASCOPE-RES-16K
    6. 5943
    Prev
    Next
    INDEX
    Explanations

    instances of legal actions or events described in a case

    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
     Puoi
    -0.41
    だが
    -0.40
    だよ
    -0.38
    TProtocol
    -0.38
     solltest
    -0.37
     puoi
    -0.37
    cesz
    -0.37
     твоя
    -0.36
     dieťa
    -0.36
     deiner
    -0.36
    POSITIVE LOGITS
     Mr
    4.25
    Mr
    3.77
     mr
    2.75
     Ms
    2.20
     Mrs
    2.20
    mr
    2.14
     Messrs
    2.05
     آقای
    2.05
     MR
    1.96
    Mrs
    1.87
    Activations Density 0.664%

    No Known Activations