© 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. 35-GEMMASCOPE-RES-16K
    11. 6986
    Prev
    Next
    INDEX
    Explanations

    statistical analysis methods and their application in research studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     respetar
    -0.40
     llorando
    -0.33
     osserv
    -0.32
     desecha
    -0.31
     Abonnez
    -0.31
     töö
    -0.30
     gjø
    -0.29
     imprimible
    -0.29
     Verbesserung
    -0.29
     väli
    -0.29
    POSITIVE LOGITS
     regression
    1.47
     Regression
    1.33
     linear
    1.20
     regressions
    1.19
    regression
    1.16
     Linear
    1.14
     logistic
    1.07
    Regression
    1.06
    Linear
    1.05
     regress
    0.98
    Activations Density 2.063%

    No Known Activations