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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3457
    Prev
    Next
    INDEX
    Explanations

    terms related to legal concepts and frameworks

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

    Latin or legal terminology and formal academic/legal language patterns.

    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
    السكان
    -0.55
    endregion
    -0.54
     שוליים
    -0.50
    üstü
    -0.49
    intios
    -0.49
    وردار
    -0.48
     Autorizaciones
    -0.47
     Italijani
    -0.47
     bağlantılar
    -0.47
    .‏
    -0.46
    POSITIVE LOGITS
    iſen
    0.48
     IERC
    0.46
    SourceChecksum
    0.45
    SPIR
    0.44
    pecabe
    0.44
    chtes
    0.44
    ValueStyle
    0.43
     Voulez
    0.42
    bitField
    0.42
    AccessorTable
    0.42
    Activations Density 0.481%

    No Known Activations