© 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. 27-GEMMASCOPE-RES-16K
    11. 9075
    Prev
    Next
    INDEX
    Explanations

    language related to rules, regulations, and criteria in legal or administrative contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الرياضيه
    -0.49
    艋
    -0.47
     دیکھیے
    -0.47
    Blaðsíða
    -0.44
    Bioaccumulative
    -0.44
    исленность
    -0.43
     oprot
    -0.43
     ivelany
    -0.42
    Personensuche
    -0.41
    chieht
    -0.41
    POSITIVE LOGITS
     certain
    2.30
    certain
    1.95
     Certain
    1.93
    Certain
    1.90
     tertentu
    1.66
     particular
    1.66
     bestimmten
    1.66
     bestimmte
    1.64
     CERTAIN
    1.61
     specific
    1.60
    Activations Density 0.976%

    No Known Activations