© 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. 37-GEMMASCOPE-RES-16K
    11. 1157
    Prev
    Next
    INDEX
    Explanations

    content related to transformations and processes involving knowledge and communication

    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
     WebDriverWait
    -0.51
    endphp
    -0.51
    TestingModule
    -0.47
    AddTagHelper
    -0.46
    脚注の使い方
    -0.46
    entile
    -0.45
    
    -0.44
    DoubleQuotes
    -0.43
    EDEFAULT
    -0.41
    FormTagHelper
    -0.40
    POSITIVE LOGITS
     about
    4.09
    about
    3.06
    About
    2.78
     ABOUT
    2.72
     About
    2.69
     tentang
    2.61
     tungkol
    2.38
    ABOUT
    2.19
     acerca
    2.19
    关于
    2.17
    Activations Density 2.524%

    No Known Activations