© 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 EvalsExportsinterp-engineNEWAPI 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. 5782
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to transcription factors and genetic elements

    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
    parsedMessage
    -0.52
     commerciali
    -0.46
    IntoConstraints
    -0.46
    AutoField
    -0.43
    RenderAtEndOf
    -0.42
    wapV
    -0.41
    AnchorStyles
    -0.41
    EDEFAULT
    -0.41
     zło
    -0.41
     Kette
    -0.40
    POSITIVE LOGITS
     transcription
    0.85
     Transcription
    0.79
    Transcription
    0.78
     promoter
    0.76
     chromatin
    0.74
     promoters
    0.72
    transcription
    0.71
     transcriptional
    0.68
     Promoter
    0.68
    prom
    0.66
    Activations Density 1.744%

    No Known Activations