© 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. 21-GEMMASCOPE-RES-16K
    11. 13325
    Prev
    Next
    INDEX
    Explanations

    terms related to medical facilities and legal terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nadel
    -0.41
     California
    -0.40
     Greenberg
    -0.39
     Greenwich
    -0.38
     Berliner
    -0.38
    prepareStatement
    -0.37
    LLYWOOD
    -0.37
     Atlanta
    -0.36
     Schäfer
    -0.34
     Berkeley
    -0.34
    POSITIVE LOGITS
    UnusedPrivate
    0.65
    Iowa
    0.62
     Amish
    0.61
     prairie
    0.60
    TintMode
    0.58
    Nebraska
    0.57
    Prairie
    0.56
    Rural
    0.56
    iowa
    0.56
     canola
    0.55
    Activations Density 0.411%

    No Known Activations