© 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. 37-GEMMASCOPE-RES-16K
    11. 3753
    Prev
    Next
    INDEX
    Explanations

    words related to legal issues and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſta
    -0.63
     faſt
    -0.58
     ſte
    -0.56
     deſt
    -0.56
     purpoſe
    -0.56
     raiſ
    -0.56
     ſtand
    -0.54
     pleaſure
    -0.52
     houſe
    -0.52
    transQ
    -0.52
    POSITIVE LOGITS
    withstanding
    0.59
     inilah
    0.59
    versing
    0.56
    timately
    0.56
     itulah
    0.55
    earing
    0.54
    ditionally
    0.54
    taining
    0.54
    ending
    0.52
    sequently
    0.52
    Activations Density 0.779%

    No Known Activations