© 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. 38-GEMMASCOPE-RES-16K
    11. 13146
    Prev
    Next
    INDEX
    Explanations

    parts of legal terminology and references in legal cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     OMITBAD
    -0.44
    oredCriteria
    -0.43
     oprot
    -0.42
     المعيارى
    -0.41
     Wikiseite
    -0.37
     fraî
    -0.37
     normalidad
    -0.36
    CppMethod
    -0.36
    atasaray
    -0.36
    enumii
    -0.35
    POSITIVE LOGITS
     New
    3.25
    New
    2.98
     NEW
    2.06
    NEW
    1.96
     뉴
    1.91
    ニュー
    1.80
     Nueva
    1.80
    新
    1.75
     Нью
    1.74
     न्यू
    1.63
    Activations Density 1.069%

    No Known Activations