© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 27-GEMMASCOPE-RES-16K
    11. 8591
    Prev
    Next
    INDEX
    Explanations

    references to biological measurements and responses in experimental contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     microbiome
    -0.71
     Bioinformatics
    -0.71
     genomics
    -0.67
     Genomics
    -0.66
     stakeholders
    -0.65
     sourced
    -0.65
     incentiv
    -0.65
     leveraging
    -0.64
     scaffold
    -0.63
     impactful
    -0.63
    POSITIVE LOGITS
    faßt
    0.64
     daß
    0.45
     Einfluß
    0.42
    luß
    0.40
     Schluß
    0.40
     USSR
    0.39
    USSR
    0.36
    FieldNumber
    0.36
     läßt
    0.36
     presunto
    0.35
    Activations Density 2.138%

    No Known Activations