© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 2387
    Prev
    Next
    INDEX
    Explanations

    connections between family history and personal health experiences

    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
    tagHelperRunner
    -0.65
    出版年
    -0.48
    /*
    -0.47
    Datuak
    -0.45
    mantec
    -0.45
    StatusCodes
    -0.45
    MENAFN
    -0.45
    bekistan
    -0.44
    WriteAttribute
    -0.42
     AssemblyCulture
    -0.42
    POSITIVE LOGITS
     daughter
    1.36
     family
    1.34
     dad
    1.34
     wife
    1.28
     daughters
    1.27
     brother
    1.26
     nephew
    1.25
     cousin
    1.23
     son
    1.23
     father
    1.23
    Activations Density 0.699%

    No Known Activations