© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 36-GEMMASCOPE-RES-16K
    11. 13897
    Prev
    Next
    INDEX
    Explanations

    phrases indicating legal proceedings or concepts related to the law

    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
    +#+#
    -0.47
     astore
    -0.40
    :"-"`
    -0.36
     arşivlendi
    -0.35
    +:+
    -0.33
     istore
    -0.31
    Eacute
    -0.31
     Bucure
    -0.30
     Câ
    -0.30
    ('/:
    -0.30
    POSITIVE LOGITS
    InjectAttribute
    0.75
    uxxxx
    0.66
     queſta
    0.63
    Скачать
    0.62
     IBRARY
    0.57
     vrijwilli
    0.56
     >=",
    0.56
    ⁧
    0.55
    Vidite
    0.54
     samfun
    0.54
    Activations Density 1.532%

    No Known Activations