© 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. 36-GEMMASCOPE-RES-16K
    6. 11385
    Prev
    Next
    INDEX
    Explanations

    legal and formal terms related to financial regulations and obligations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     now
    -0.52
     probably
    -0.52
    probably
    -0.52
     many
    -0.48
     why
    -0.45
     luckily
    -0.43
     here
    -0.43
     Pourtant
    -0.42
    perhaps
    -0.41
     ironically
    -0.41
    POSITIVE LOGITS
    Any
    0.82
     Any
    0.81
     Failure
    0.79
    Failure
    0.77
     cualquier
    0.74
     any
    0.72
     Upon
    0.72
     Exceptions
    0.71
     failure
    0.71
     unless
    0.69
    Activations Density 0.641%

    No Known Activations