© 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-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 13007
    Prev
    Next
    INDEX
    Explanations

    references to arterial oxygen saturation levels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ```
    -0.69
     Withers
    -0.69
     fila
    -0.66
    <h2>
    -0.64
     Minden
    -0.63
     compro
    -0.63
     tren
    -0.61
     Wheeler
    -0.59
     animo
    -0.58
     platt
    -0.58
    POSITIVE LOGITS
    Sa
    2.81
     Sa
    2.79
     sa
    2.34
    sa
    2.31
     SA
    2.29
    SA
    2.22
     Sadie
    1.71
     Saar
    1.60
     SAH
    1.58
     Sá
    1.53
    Activations Density 0.131%

    No Known Activations