© 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. 15-GEMMASCOPE-RES-16K
    11. 1234
    Prev
    Next
    INDEX
    Explanations

    references to legal terms and formal statements in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AsyncResult
    -0.54
    cvtColor
    -0.53
     downvoted
    -0.53
     Sandler
    -0.53
    évaluateur
    -0.52
     Garnett
    -0.51
     eddy
    -0.51
     scrapbook
    -0.50
    setAccessible
    -0.49
    mulos
    -0.49
    POSITIVE LOGITS
     listed
    0.73
     Mentioned
    0.65
     mention
    0.65
     mentioned
    0.64
     specified
    0.63
     specify
    0.63
     Listed
    0.62
    Listed
    0.60
     nakalista
    0.60
    mentioned
    0.59
    Activations Density 0.555%

    No Known Activations