© 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. 35-GEMMASCOPE-RES-16K
    11. 7648
    Prev
    Next
    INDEX
    Explanations

    specific phrases regarding decision-making in legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    それとも
    -0.50
     rootView
    -0.47
     yyq
    -0.45
     carc
    -0.44
    UFACT
    -0.44
    下载附件
    -0.43
     &___
    -0.43
     cæ
    -0.41
     iNdEx
    -0.41
    enough
    -0.41
    POSITIVE LOGITS
     latter
    3.42
     former
    2.55
    latter
    2.48
    后者
    2.42
    Former
    2.02
    former
    1.98
     Former
    1.97
     letz
    1.70
     Latter
    1.59
     senare
    1.54
    Activations Density 0.736%

    No Known Activations