© 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. 31-GEMMASCOPE-RES-16K
    11. 11590
    Prev
    Next
    INDEX
    Explanations

    references to legal principles and judicial conduct

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    legal case citations and court opinions formatted with volume numbers, reporter abbreviations, and page numbers.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    QMetaType
    -0.60
    出版年
    -0.54
     iprot
    -0.51
    saraba
    -0.49
     BoxFit
    -0.48
    MigrationBuilder
    -0.48
    AndEndTag
    -0.47
    ніципалі
    -0.46
    tagHelperRunner
    -0.45
     يتيمه
    -0.45
    POSITIVE LOGITS
    Page
    0.43
     Page
    0.40
     Италијани
    0.36
     |
    0.36
     />';
    0.36
     Seite
    0.35
     ]}
    0.35
    astify
    0.35
     AppCompatTheme
    0.35
    |]
    0.35
    Activations Density 0.472%

    No Known Activations