© 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. 37-GEMMASCOPE-RES-16K
    11. 4056
    Prev
    Next
    INDEX
    Explanations

    technical language related to data handling and processing in computing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ConstraintMaker
    -0.63
    IntoConstraints
    -0.59
     AssemblyProduct
    -0.56
    TagMode
    -0.52
     MainAxisSize
    -0.50
    يكب
    -0.50
     AssemblyTitle
    -0.50
    etCode
    -0.49
     Paglinawan
    -0.47
    UnitTesting
    -0.47
    POSITIVE LOGITS
     data
    3.27
    data
    2.55
     Data
    2.50
    データ
    2.48
     Daten
    2.45
    数据
    2.41
     DATA
    2.38
    Data
    2.27
     데이터
    2.20
     données
    2.16
    Activations Density 1.943%

    No Known Activations