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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 1898
    Prev
    Next
    INDEX
    Explanations

    references to sentences and sentencing within a legal context

    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
     ویکی‌پدی
    -0.73
    Personendaten
    -0.73
     يتيمه
    -0.67
     kaarangay
    -0.60
    ErrUnexpectedEOF
    -0.60
     AssemblyCulture
    -0.57
    FunctionFlags
    -0.57
    lectic
    -0.56
    hoeddwyd
    -0.55
    IndentedString
    -0.55
    POSITIVE LOGITS
     sentence
    1.26
     sentences
    1.04
     phrase
    0.99
     Sentence
    0.94
     clause
    0.90
    sentence
    0.87
     Clause
    0.84
     Sentences
    0.84
     Phrase
    0.78
    phrase
    0.77
    Activations Density 0.136%

    No Known Activations