© 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. 19-GEMMASCOPE-RES-16K
    11. 4715
    Prev
    Next
    INDEX
    Explanations

    phrases indicating medical conditions or physical diagnostics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UserScript
    -0.74
     يتيمه
    -0.72
    <bos>
    -0.67
    Datuak
    -0.63
     Alors
    -0.61
     panelists
    -0.59
    XmlAccessorType
    -0.57
     iNdEx
    -0.57
    ImageContext
    -0.57
    哪个
    -0.56
    POSITIVE LOGITS
     propOrder
    0.66
     wide
    0.62
     Vielzahl
    0.57
     mix
    0.55
     large
    0.55
    variety
    0.54
     variety
    0.52
     profusion
    0.51
    jooq
    0.51
    VersionUID
    0.51
    Activations Density 0.364%

    No Known Activations