© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 9421
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts and terms related to integration and probability density functions

    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
    yorsunuz
    -0.40
    rsiniz
    -0.37
     HasFactory
    -0.33
    sessionStorage
    -0.29
     мани
    -0.28
    дак
    -0.28
    bigliamento
    -0.28
    ंदीखरीदारी
    -0.28
    vern
    -0.27
    ępo
    -0.27
    POSITIVE LOGITS
     integration
    3.70
     integrate
    3.47
     Integration
    3.44
     integrating
    3.25
     INTEGR
    3.23
     integrated
    3.22
    Integration
    3.17
     Integrate
    3.13
     integrates
    3.13
    integration
    3.09
    Activations Density 1.518%

    No Known Activations