© 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. 36-GEMMASCOPE-RES-16K
    11. 14576
    Prev
    Next
    INDEX
    Explanations

    phrases related to regulations and conditions surrounding the provision and management of data and resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumii
    -0.75
     مرئيه
    -0.59
     للاسماء
    -0.58
    ंदीखरीदारी
    -0.57
    VYMaps
    -0.53
    DebuggerStep
    -0.50
    Diweddarwch
    -0.49
     للمعارف
    -0.49
     bezeichneter
    -0.48
    脚注の使い方
    -0.48
    POSITIVE LOGITS
     up
    2.75
     upto
    2.19
    upto
    1.78
     jusqu
    1.74
    up
    1.63
     Up
    1.59
    Up
    1.58
     hasta
    1.55
    jusqu
    1.45
     até
    1.41
    Activations Density 1.569%

    No Known Activations