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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 4278
    Prev
    Next
    INDEX
    Explanations

    scientific studies related to health and disease research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Gambas
    -0.54
     Already
    -0.41
     lenker
    -0.39
     famed
    -0.38
     aka
    -0.38
     fameux
    -0.37
     Modern
    -0.36
    ulling
    -0.36
     fare
    -0.35
     pedest
    -0.35
    POSITIVE LOGITS
     study
    1.16
     findings
    1.08
     paper
    1.00
     estudo
    0.92
     penelitian
    0.92
     investigación
    0.89
     research
    0.88
     authors
    0.86
     studies
    0.84
     experiments
    0.84
    Activations Density 2.310%

    No Known Activations