© 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. 7237
    Prev
    Next
    INDEX
    Explanations

    references to specific demographics, particularly healthy individuals or patient groups in research contexts

    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
     cref
    -0.40
    andExpect
    -0.40
    __(/*!
    -0.37
     angef
    -0.37
     мәкал
    -0.35
     متعلقه
    -0.34
     auxquelles
    -0.31
     otomatig
    -0.31
     воспита
    -0.30
     чу
    -0.30
    POSITIVE LOGITS
     healthy
    1.04
     individuals
    1.00
    healthy
    0.90
     adults
    0.90
    individuals
    0.89
     adolescents
    0.88
     subjects
    0.86
     females
    0.84
    Healthy
    0.84
     males
    0.83
    Activations Density 1.845%

    No Known Activations