© 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. 2439
    Prev
    Next
    INDEX
    Explanations

    references to caregiving and support for aging loved ones

    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
    ItemBackground
    -0.97
    fjspx
    -0.88
    InjectAttribute
    -0.87
     AssemblyCulture
    -0.86
    RegressionTest
    -0.78
    AndEndTag
    -0.77
     Vikipedi
    -0.76
    ThroughAttribute
    -0.76
     سكانية
    -0.75
    OrNil
    -0.74
    POSITIVE LOGITS
     loved
    1.58
     someone
    1.56
    someone
    1.41
     person
    1.28
     somebody
    1.26
    Someone
    1.25
     Someone
    1.24
    loved
    1.16
    somebody
    1.15
     Loved
    1.14
    Activations Density 0.144%

    No Known Activations